ML Conference Papers | NeurIPS, CVPR, ACL, ICCV, EMNLP Analysis

ACL 2025

Association for Computational Linguistics 4,729 papers

+

Language Model Evaluation 393

Assessing and evaluating language models beyond traditional benchmarks focusing on bias and robustness in diverse contexts.

evaluation metrics (1)

Sub-topics:

Benchmarking LLM Performance (133)

Error Correction Techniques (70)

Bias Evaluation Methods (52)

Retrieval-Augmented Generation (44)

Dynamic Response Sampling (36)

Human-in-the-Loop Evaluation (34)

(Dis)improved?! How Simplified Language Affects Large Language Model Performance... (Towards) Scalable Reliable Automated Evaluation with Large Language Models 100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Co...

Fine-Grained Multimodal Reasoning 199

Techniques for enhancing reasoning capabilities across various data modalities at the sentence level.

sentence-level optimizationadaptive algorithmsmultimodal interactionspreference modeling

Sub-topics:

Contextual Comprehension Frameworks (67)

Adaptive Multimodal Retrieval Techniques (45)

Multimodal Knowledge Integration (36)

Bias Mitigation in Multimodal Learning (21)

Multi-Agent Collaborative Reasoning (15)

Fine-Grained Emotion Recognition (15)

1-2-3 Check: Enhancing Contextual Privacy inLLMvia Multi-Agent Reasoning 111DUTatSemEval-2025 Task 8:Hierarchical Chain-of-Thought Reasoning and Multi-Mo... 5cNLPatBioLaySumm2025: Prompts, Retrieval, and Multimodal Fusion

Automated Communication Skills Assessment 62

Automating the scoring system to evaluate communication skills in healthcare settings, focusing on performance and scalability.

physician-patient interactioncommunication scoringclinical assessmentsnatural language processing

A Comprehensive Taxonomy of Bias Mitigation Methods for Hate Speech Detection A Continuous Approach to Metaphorically Motivated Regular Polysemy in Language M... A General Framework to Enhance Fine-tuning-basedLLMUnlearning

Multimodal Emotion Recognition 60

Research focused on bridging gaps in human-annotated datasets for emotion recognition in multiple languages.

emotion classification (1)

2M-BELEBELE: Highly Multilingual Speech andAmericanSignLanguage Comprehension Da... A Large and Balanced Corpus for Fine-grainedArabic Readability Assessment A Parameter-Efficient and Fine-Grained Prompt Learning for Vision-Language Model...

Error Detection in CAD Systems 57

Utilizing AI to automate the review process of CAD programs for error detection and correction.

error correction (3)

A Dual-PerspectiveNLGMeta-Evaluation Framework with Automatic Benchmark and Bett... A Framework for Fine-Grained Complexity Control in Health Answer Generation A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Gra...

Contextual Document Retrieval 52

Improving retrieval techniques using context-aware methods to enhance document access and relevance.

context-aware alignmentdocument retrieval techniquesLLM generationknowledge graphs

A Case Study of Cross-Lingual Zero-Shot Generalization for Classical Languages i... A Dual-Layered Evaluation of Geopolitical and Cultural Bias inLLMs A Fully Generative Motivational Interviewing Counsellor Chatbot for Moving Smoke...

Bias in Political Decision-Making 42

Analyzing how biases within language models can impact political decisions and public discourse.

language model biasinfluence on politicsethical implicationsdecision-making analysis

(Fact) Check Your Bias 7 Points toTsinghua but 10 Points to ? Assessing Large Language Models in Agenti... A Computational Framework to Identify Self-Aspects in Text

Commonsense Reasoning in Language Models 38

Exploration and benchmarking of commonsense reasoning abilities within large language models for complex tasks.

commonsense knowledge (1)large language models (3)

(RSA)²: A Rhetorical-Strategy-Aware Rational Speech Act Framework for Figurative... A Classifier of Word-Level Variants in Witnesses of BiblicalHebrew Manuscripts A Measure of the System Dependence of Automated Metrics

Adaptive Quantization Techniques 29

Developing adaptive quantization techniques to improve performance and efficiency in AI model inference.

quantization strategiesoutlier detectionresource-efficient modelsfloating-point representation

3DM: Distill, Dynamic Drop, and Merge for Debiasing Multi-modal Large Language M... A Retrieval-Based Approach to Medical Procedure Matching inRomanian A2ATS: Retrieval-BasedKVCache Reduction via Windowed Rotary Position Embedding a...

Hate Speech Detection 25

Investigating advanced methods for detecting and analyzing hate speech and harassment in online platforms.

transphobic hate (1)

A Linguistically Motivated Analysis of Intonational Phrasing in Text-to-Speech S... A Little Human Data Goes A Long Way A Modular Taxonomy for Hate Speech Definitions and Its Impact on Zero-ShotLLMCla...

AFA 2025

American Finance Association Annual Meeting 83 papers

+

Long-Term Behavioral Finance 14

Examining how historical socio-political events influence long-standing attitudes toward investment practices and financial market participation.

attitudes (1)financial markets (1)

The Long‐Lasting Effects of Experiencing Communism on Attitudes toward Financial... ISSUE INFORMATION Presidential Address: Housing Betas

FinTech Credit Impact 14

Investigating how the adoption of cashless payment methods influences borrowers' access to capital and risk profiles in FinTech lending.

FinTech lending (1)cashless payments (1)

FinTech Lending and Cashless Payments Can Social Media Inform Corporate Decisions? Evidence from Merger Withdrawals AMERICAN FINANCE ASSOCIATION

Internal Organization Post-IPO 12

Examining organizational transformations within firms following their transition to public ownership through IPOs.

initial public offerings (1)

Going Public and the Internal Organization of the Firm Value without Employment The Stock Market and Bank Risk‐Taking

Corporate Social Impact Measurement 10

Conceptualizing and quantifying social impact in corporate contexts and its implications for stakeholder engagement.

impact investing (1)stakeholder capitalism (1)social impact (1)

An Economic View of Corporate Social Impact Privacy and Team Incentives ISSUE INFORMATION

Debt Discharge Effects 10

Evaluating the impact of random debt discharge episodes on the financial behavior and outcomes of student borrowers.

student debt relief (1)borrower outcomes (1)

Second Chance: Life with Less Student Debt Asset Pricing and Risk‐Sharing Implications of Alternative Pension Plan Systems Going for Broke: Bank Reputation and the Performance of Opaque Securities

Supply Chain Uncertainty Analysis 8

Analyzing the effects of uncertainty shocks within supply chains on firm-level economic decisions and production strategies.

upstream uncertainty (1)downstream uncertainty (1)economic activity (1)

Investment under Upstream and Downstream Uncertainty Green Window Dressing Forest through the Trees: Building Cross‐Sections of Stock Returns

Loan Covenant Evolution 8

Analyzing the decline in loan covenant violations among public firms and the factors influencing covenant design.

covenant violations (1)public firms (2)covenant design (1)

Losing Control? The Two‐Decade Decline in Loan Covenant Violations The Imperfect Intermediation of Money‐Like Assets CEO Stress, Aging, and Death

Portfolio Choice Dynamics 5

Studying the influence of risk preferences and behavioral frictions on investors' portfolio choices in retirement accounts.

portfolio choice (1)risk preferences (1)

What Drives Investors' Portfolio Choices? Separating Risk Preferences from Frict... Pockets of Predictability: A Replication The “Actual Retail Price” of Equity Trades

ESG Impact on Firm Valuation 5

Assessing how negative ESG news affects analysts' valuation forecasts and the consequent implications for firm value.

environmental governancesocial impactfirm valueanalyst forecasts

Paying Too Much? Borrower Sophistication and Overpayment in the U.S. Mortgage Ma... Anomalies and Their Short‐Sale Costs Long‐Horizon Exchange Rate Expectations

Social Media Sentiment Analysis 2

Investigating the correlation between social media sentiment and corporate merger withdrawal decisions.

merger withdrawalssocial mediasentiment trackingpredictive modeling

Adverse Selection in Corporate Loan Markets ESG News, Future Cash Flows, and Firm Value

CVPR 2025

Computer Vision and Pattern Recognition 2,881 papers

+

3D Reconstruction Methods 175

Focuses on techniques for reconstructing 3D models and scenes from various data inputs, including images and LiDAR data.

LiDAR segmentation (1)camera pose (1)

Sub-topics:

3D Scene Understanding (79)

Sparse Representation for 3D (39)

3D Object Detection (27)

3D Gaussian Splatting (11)

Multi-view Reconstruction (11)

Monocular 3D Reconstruction (8)

2DMamba: Efficient State Space Model for Image Representation with Applications ... 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes 3D Dental Model Segmentation with Geometrical Boundary Preserving

Diffusion Model Architectures 164

Research focuses on the development and refinement of diffusion models for tasks such as image generation, compression, and perception.

image generation (4)region adaptive (1)

Sub-topics:

3D Object Generation (52)

Post-Training Optimization (42)

Adaptive Sampling Techniques (30)

Semantic Understanding in Diffusion (20)

Contrastive Learning Approaches (19)

3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion 4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Model...

Multimodal Learning Techniques 136

Explores methods for integrating and understanding data across multiple modalities to enhance learning outcomes.

text-image integrationaudio-visual perceptionmultimodal retrievalgesture generation

Sub-topics:

Multimodal Fusion Techniques (41)

Adaptive Learning Strategies (35)

Multimodal Data Generation (30)

Multimodal Interaction Analysis (12)

Cross-Modal Alignment (10)

Benchmarking Multimodal Models (8)

4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Tra... A Unified Image-Dense Annotation Generation Model for Underwater Scenes

Geometric and Spatial Reasoning 94

Focuses on mechanisms to leverage geometric and spatial information for refined reasoning in visual and multimodal contexts.

spatial-temporal reasoning (1)

A Hubness Perspective on Representation Learning for Graph-Based Multi-View Clus... ABBSPO: Adaptive Bounding Box Scaling and Symmetric Prior based Orientation Pred... AKiRa: Augmentation Kit on Rays for Optical Video Generation

Incremental Learning Strategies 92

Develops methodologies for learning new information sequentially while retaining previously acquired knowledge efficiently.

class-incremental learning (2)continual learning (2)

5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition... A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation A Dataset for Semantic Segmentation in the Presence of Unknowns

Data Distillation Methods 71

Investigates techniques for improving the efficiency and effectiveness of training sets through selective refinement and distillation.

non-critical region (1)

4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating La... ADD: Attribution-Driven Data Augmentation Framework for Boosting Image Super-Res...

Zero-Shot Learning and Attribution 68

Investigates strategies for model performance in recognizing and attributing data in unseen scenarios without explicit training.

source attribution (1)anomaly detection (2)

3D Prior Is All You Need: Cross-Task Few-shot 2D Gaze Estimation A Focused Human Body Model for Accurate Anthropometric Measurements Extraction A Theory of Learning Unified Model via Knowledge Integration from Label Space Va...

Motion and Pose Estimation 63

Focusing on methods for accurately estimating motion and pose in various contexts, especially from the user's perspective.

egocentric vision (1)

Align-A-Video: Deterministic Reward Tuning of Image Diffusion Models for Consist... Align3R: Aligned Monocular Depth Estimation for Dynamic Videos AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignme...

Natural Language Alignment Techniques 54

Studies methods for aligning textual instructions and outputs with corresponding visual or motion-related tasks.

text-to-motioninstruction tuningGPT alignmentevent-level coordination

A Distractor-Aware Memory for Visual Object Tracking with SAM2 A Simple yet Effective Layout Token in Large Language Models for Document Unders... ACE: Anti-Editing Concept Erasure in Text-to-Image Models

Graph-Based Learning Approaches 47

Explores the use of graph structures for learning tasks, particularly in scenarios with privacy considerations and distributed data.

federated learning (5)graph neural networks (1)homophily heterogeneity (1)

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning A General Adaptive Dual-level Weighting Mechanism for Remote Sensing Pansharpeni... ALIEN: Implicit Neural Representations for Human Motion Prediction under Arbitra...

EMNLP 2025

Empirical Methods in Natural Language Processing 4,361 papers

+

Text Generation Task Analysis 156

Analyzing and improving techniques for generating coherent and creative text outputs in various contexts.

story generation (1)pun generation (1)

Sub-topics:

Evaluation Frameworks for Text Generation (58)

Adaptive Prompting Techniques (25)

Bias and Fairness in LLMs (20)

Multi-agent Collaboration for Text Generation (18)

Cognitive Models in Language Production (18)

Improving Consistency in Generated Text (17)

3R: Enhancing Sentence Representation Learning via Redundant Representation Redu... A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augme... A Culturally-diverse Multilingual Multimodal Video Benchmark & Model

Prompt Engineering Optimization 122

Investigations into the design and optimization of prompts for enhancing language model outputs.

language models (20)

Sub-topics:

Evaluation Frameworks for Prompting (53)

Prompt Optimization Techniques (23)

Contextual Prompt Adjustments (21)

Guidelines for Multimodal Prompts (17)

Adaptive Prompt Strategies (7)

!MSAatAraHealthQA2025 Shared Task: EnhancingLLMPerformance forArabic Clinical Qu... !MSAatBARECShared Task 2025: EnsemblingArabic Transformers for Readability Asses... : Structuring Your Natural LanguageSOPs into Tailored Ambiguity-Resolve...

Cultural Knowledge Representation 122

Studies aimed at incorporating and representing cultural and religious knowledge within language models.

cultural questionsreligious knowledgedata augmentationtaxonomy-guided frameworks

Sub-topics:

Culturally-Aware Natural Language Processing (54)

Multilingual Knowledge Representation (27)

Cultural Bias in AI Systems (24)

Cross-Cultural Evaluation Metrics (12)

Representation of Cultural Narratives (4)

3LM: BridgingArabic,STEM, and Code through Benchmarking A Benchmark for Translations Across Styles and Language Variants A Benchmark forHindi Verb-Argument Structure Alternations

Multimodal Model Alignment 108

Researching techniques for aligning information and representation in multimodal models integrating various data types.

multimodal learningalignment techniquesvisual-language modelscontextual knowledge

Sub-topics:

Evaluation Metrics for Alignment (52)

Culturally-aware Multimodal Models (15)

Adaptive Fusion Strategies (15)

Symmetric Multimodal Alignment (10)

Neuro-Symbolic Techniques in Alignment (9)

Interdisciplinary Recommender Systems (7)

(Almost) Free Modality Stitching of Foundation Models 2Columns1Row: ARussian Benchmark for Textual and Multimodal Table Understanding ... 3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation

Dialog Systems and Education 100

Developments in utilizing dialog systems to enhance educational experiences and assess pedagogic effectiveness.

conversational agents (1)

Sub-topics:

Automated Student Assessment Systems (38)

Benchmarking Educational Dialogue Systems (18)

Multimodal Learning Environments (13)

Cultural Adaptation in Educational Dialogs (13)

Prompt Engineering for Educational Dialogs (9)

Explainable Chatbot Interactions (9)

A Generative Framework for Personalized Sticker Retrieval A Generative Pre-Trained Language Model for Channel Prediction in Wireless Commu... A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with...

Safety and Ethical AI 87

Research focused on the evaluation and enhancement of safety measures and ethical governance in AI implementations.

safety benchmarkingethical considerationsAI governancelanguage model assessment

A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Langua... A Comprehensive Survey on the Trustworthiness of Large Language Models in Health... A Comprehensive Taxonomy of Negation forNLPand Neural Retrievers

Evaluation of Mathematical Reasoning 83

Exploring how models perform on mathematical reasoning tasks and the evaluation of their solution strategies.

math problemsabstract reasoningcorrect solutionslanguage model evaluation

A Category-Theoretic Approach to Neural-Symbolic Task Planning with Bidirectiona... A Causal Lens for Evaluating Faithfulness Metrics A Rigorous Evaluation ofLLMData Generation Strategies for Low-Resource Languages

Bias Mitigation in Language Models 78

Efforts to identify and reduce biases within language models through various analytical and augmentation strategies.

bias analysis (1)

912 atTAQEEM2025: A Distribution-aware Approach toArabic Essay Scoring A Comparison of Elementary Baselines forBabyLM A ComprehensiveLiteraryChinese Reading Comprehension Dataset with an Evidence Cu...

Reinforcement Learning Techniques 55

Development and evaluation of reinforcement learning methods for improving model performance across various tasks.

reinforcement learning (5)posterior sampling (1)

A Comprehensive Survey on Learning from Rewards for Large Language Models: Rewar... A Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Ad... A Sequential Multi-Stage Approach for Code Vulnerability Detection via Confidenc...

Continual Learning Evaluation 47

Research focused on frameworks to evaluate and improve continual learning capabilities in language models.

continual learning (1)language models (3)

1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language M... 3DS: Medical Domain Adaptation ofLLMs via Decomposed Difficulty-based Data Selec... A Pipeline to Assess Merging Methods via Behavior and Internals

ICCV 2025

International Conference on Computer Vision 2,701 papers

+

3D Scene Reconstruction 165

Approaches for effective modeling and reconstruction of 3D scenes, including handling dynamic elements and camera motion.

Gaussian splatting (11)

Sub-topics:

Multi-View Scene Understanding (46)

Depth Estimation Techniques (32)

Object-Aware 3D Modeling (30)

3D Gaussian Splatting (22)

Monocular 3D Reconstruction (20)

2D Gaussian Splatting-based Sparse-view Transparent Object Depth Reconstruction ... 3D Mesh Editing using Masked LRMs 3D Test-time Adaptation via Graph Spectral Driven Point Shift

Diffusion Model Enhancements 155

Advancements in diffusion models addressing uncertainty, generative capabilities, and applications in various domains.

asymmetric learning (1)epistemic uncertainty (1)image generation (7)

Sub-topics:

Domain Adaptation Strategies (43)

Amodal Reconstruction Methods (37)

Guided Diffusion Frameworks (22)

Temporal Consistency in Diffusion (21)

Adaptive Sampling Techniques (18)

Diffusion Model Evaluation Metrics (13)

A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation w... A Linear N-Point Solver for Structure and Motion from Asynchronous Tracks A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Diffic...

Image Segmentation Methods 155

Techniques enhancing image segmentation models for improved accuracy and applicability across varied datasets and conditions.

semantic segmentation (8)pansharpening (1)segmentation models (1)

Sub-topics:

Multi-Modal Image Segmentation (46)

Gaussian Splatting for Segmentation (36)

Few-Shot Image Segmentation (34)

Temporal Segmentation in Video (21)

Adaptive Medical Image Segmentation (17)

A Quality-Guided Mixture of Score-Fusion Experts Framework for Human Recognition A Real-world Display Inverse Rendering Dataset A Tiny Change, A Giant Leap: Long-Tailed Class-Incremental Learning via Geometri...

Video Generation Techniques 131

Innovative methods for generating and manipulating video content, focusing on efficiency and quality.

video synthesis (1)distillation (3)motion generation (1)context perception (1)

Sub-topics:

Adaptive Video Processing (55)

3D Scene Generation (36)

Diffusion-based Video Synthesis (19)

Motion Reasoning and Generation (15)

Video Prediction Models (5)

3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage G... AD-GS: Object-Aware B-Spline Gaussian Splatting for Self-Supervised Autonomous D... AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Predicti...

Vision-Language Integration 102

Research emphasizing the synergistic interaction between vision and language for tasks like object retrieval and scene understanding.

CLIP modelsopen-set retrievalchain-of-affordancecontextual representation

Sub-topics:

3D Scene Understanding (26)

Adaptive Representation Learning (25)

Cross-Modal Interaction Learning (25)

Evaluation Benchmarks for Vision-Language Models (11)

Temporal Alignment in Multi-Modal Generation (8)

Visual Question Answering (7)

"Principal Components" Enable A New Language of Images 2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining 3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation

Event-based Vision 65

Exploration of adapting image detection models to leverage the unique characteristics of event-based vision systems.

latent space adaptation (1)image detectors (1)dynamic scenes (1)

A View-consistent Sampling Method for Regularized Training of Neural Radiance Fi... AR-1-to-3: Single Image to Consistent 3D Object via Next-View Prediction ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction

Unsupervised Anomaly Detection 61

Strategies for identifying anomalies in data through unsupervised mechanisms that leverage structural and behavioral insights.

trace guidancevelocity alignmenttop-down distillationunsupervised learning

2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Vid... A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed I... A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention

Quantization & Model Compression 51

Methods for reducing the resource footprint of machine learning models while maintaining accuracy and performance.

post-training quantization (1)

A Differentiable Wave Optics Model for End-to-End Computational Imaging System O... AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment ... AIRA: Activation-Informed Low-Rank Adaptation for Large Models

Federated Learning 45

Techniques for preserving privacy and improving generalizability in federated learning environments through innovative model architectures.

federated meta-learning (1)collaborative learning (1)

A Framework for Double-Blind Federated Adaptation of Foundation Models A Good Teacher Adapts Their Knowledge for Distillation A Unified Framework for Industrial Cel-Animation Colorization with Temporal-Stru...

Next-X Prediction 41

Research focusing on extending next-token predictive models to multi-step predictions in visual generation tasks.

autoregressive generationvisual generationmulti-step predictionpredictive modeling

AGO: Adaptive Grounding for Open World 3D Occupancy Prediction AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrar... AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Re...

ICML 2025

International Conference on Machine Learning 3,380 papers

+

Unsupervised Learning Techniques 570

This area examines methodologies for learning patterns and representations in data without label supervision or explicit guidance.

pseudo-labeling (1)imitation learning (1)

Sub-topics:

Causal Discovery Methods (115)

Self-Supervised Learning (114)

Generative Models (112)

Clustering Algorithms (76)

Dimensionality Reduction Techniques (54)

Graph-Based Unsupervised Learning (38)

Geometric Median (GM) Matching for Robust k-Subset Selection from Noisy Data Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering...

Generative Modeling Techniques 456

This area focuses on developing generative models capable of producing high-quality data samples through various training methods.

deep generative models (1)mixture distributions (1)

Sub-topics:

Generative Modeling Evaluation Metrics (154)

Generative Flow Models (142)

Latent Space Optimization (39)

Multimodal Generative Synthesis (30)

Conditional Generative Models (29)

Generative Adversarial Networks (GANs) (25)

Aggregation of Dependent Expert Distributions in Multimodal Variational Autoenco... An in depth look at the Procrustes-Wasserstein distance: properties and barycent... From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, ...

Natural Language Processing Techniques 390

This domain investigates specific methodologies for understanding and generating human language, including tokenization and parsing techniques.

language modeling (2)

Sub-topics:

Transfer Learning in NLP (111)

Evaluation of Language Models (76)

Text Generation Models (62)

Fairness in Language Models (48)

Multimodal Language Processing (42)

Knowledge Distillation in NLP (26)

Consensus Is All You Get: The Role of Attention in Transformers Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts La... Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with ...

Reinforcement Learning from Feedback 344

This topic focuses on enhancing reinforcement learning through feedback-driven methods, including safety mechanisms and multi-objective optimizations.

RLHF (5)multi-objective (6)

Sub-topics:

Sample Efficiency in RL (199)

Feedback Integration Techniques (74)

Exploration Strategies in RL (18)

Multi-task Reinforcement Learning (17)

Safe Reinforcement Learning (14)

Interactive Reinforcement Learning (9)

LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models NextCoder: Robust Adaptation of Code LMs to Diverse Code Edits The Surprising Effectiveness of Test-Time Training for Few-Shot Learning

Large Language Model Alignment 303

This topic centers around aligning large language models with human-like reasoning, safety metrics, and task-specific requirements.

safety alignment (1)fine-tuning (11)multimodal LLMs (2)large language models (35)

Sub-topics:

Task Generalization Techniques (81)

Robustness to Distribution Shift (63)

Evaluating Alignment in Context (46)

Fine-tuning Strategies (44)

Multimodal Learning Approaches (26)

Interpretable Alignment Metrics (24)

Star Attention: Efficient LLM Inference over Long Sequences AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improvi... Differentiable Quadratic Optimization For the Maximum Independent Set Problem

Graph Neural Networks 256

This area investigates the application and adaptation of graph models and spectral techniques for processing and learning from graph-structured data.

node representation (1)

Sub-topics:

Graph Neural Network Generalization Techniques (96)

Graph-Based Algorithms for Similarity Search (44)

Dynamic Graph Learning Methods (42)

Benchmarking Graph Neural Networks (25)

Graph Transformer Architectures (23)

Robust Graph Anomaly Detection (17)

Improved Approximations for Hard Graph Problems using Predictions Graph Neural Network Generalization With Gaussian Mixture Model Based Augmentati... Design Considerations in Offline Preference-based RL

Federated and Privacy-Preserving Learning 251

This topic investigates techniques for training models across decentralized datasets while maintaining user privacy and data protection.

federated learning (12)

Sub-topics:

Robustness to Adversarial Distribution Shifts (58)

Decentralized Learning Mechanisms (57)

Trustworthy Federated Learning (55)

Weight Averaging Techniques (35)

Adaptive Protocols for Privacy (25)

Private Quantile Estimation (16)

Lightweight Protocols for Distributed Private Quantile Estimation Breaking the n¹.5 Additive Error Barrier for Private and Efficient Graph Sparsif... The Missing Alignment Link of In-context Learning on Sequences

Meta-Learning Approaches 221

This topic covers the study of learning algorithms that improve their performance on tasks through the adaptation of learning strategies themselves.

optimization methodshyperparameter tuninglearning to learnadaptive algorithms

Sub-topics:

Task Generalization Techniques (81)

Dynamic Model Adaptation (69)

Performance Benchmarking in Meta-Learning (25)

Knowledge Distillation Approaches (19)

Multi-Task Learning Algorithms (16)

Federated Learning in Meta-Learning (9)

Task Generalization with Autoregressive Compositional Structure: Can Learning fr... Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging Otter: Generating Tests from Issues to Validate SWE Patches

Image Generation and Customization 216

This field explores methods for generating and customizing images based on specific attributes or contextual information.

diffusion models (6)

Sub-topics:

Generative Model Improvements (124)

Evaluation Benchmarks for Generative Models (41)

Data Augmentation Strategies (18)

Multi-modal Image Generation (11)

Diffusion Model Applications (11)

Adaptive Convolution Techniques (6)

Nesterov Method for Asynchronous Pipeline Parallel Optimization Adaptive Estimation and Learning under Temporal Distribution Shift Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identificat...

Defensive Strategies in AI 211

This field examines methods to enhance the robustness and safety of AI models against various forms of attacks and vulnerabilities.

adversarial attacks (2)

Sub-topics:

Robust Neural Network Architectures (132)

Model Calibration Under Uncertainty (33)

Evaluation Benchmarks for Robustness (19)

Privacy-Preserving Learning Techniques (14)

Adversarial Training Approaches (5)

Unlearning and Data Removal Techniques (5)

EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vul... FedECADO: A Dynamical System Model of Federated Learning GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model

NAACL 2025

North American Chapter of ACL 1,957 papers

+

Causal Learning in NLP 497

Research focused on applying causal learning methods to address spurious correlations in natural language processing tasks.

causal inference (2)spurious correlations (1)text classification (4)

Sub-topics:

Causal Benchmarks for Language Understanding (137)

Causal Impact Analysis of Language Generation (85)

Causal Mechanisms in Dialogue Systems (80)

Causal Interpretability of Language Models (71)

Identifying Causal Features in Text (59)

Causal Inference in Language Models (38)

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the... Benchmarking Distributional Alignment of Large Language Models Improving and Assessing the Fidelity of Large Language Models Alignment to Onlin...

Data Augmentation Techniques 347

Techniques for enhancing training datasets, particularly focusing on few-shot scenarios and relation extraction tasks.

relation extraction (4)

Sub-topics:

Dynamic Data Augmentation (108)

Contextual Data Enrichment (80)

Multi-Modal Augmentation (64)

Label-Free Data Filtering (36)

Noise-Enhanced Training (30)

Sampling Strategies for Imbalanced Datasets (25)

ALTER: Augmentation for Large-Table-Based Reasoning MADSpeech: Measures of Acoustic Diversity of Speech Fingerspelling within Sign Language Translation

Multimodal Learning Systems 221

Exploring the integration of multiple modalities, such as text and audio, to improve performance in specific tasks like clinical forecasting.

multimodal transformersclinical forecastinghybrid approachesaudio-visual integration

Sub-topics:

Contextualized Multimodal Understanding (52)

Cross-Modal Learning Techniques (47)

Bias and Fairness in Multimodal Models (45)

Multimodal Evaluation Benchmarks (41)

Adaptive Multimodal Representation (23)

Visual Question Answering Frameworks (7)

Understanding Figurative Meaning through Explainable Visual Entailment MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Gen... MoDS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries i...

Unlimited Reasoning Capabilities 218

Enhancing reasoning capabilities of models through innovative techniques like reverse thinking and step-by-step reasoning frameworks.

chain-of-thoughtlogical reasoningmodels verificationreverse thinking

Sub-topics:

Dynamic Context Adaptation (47)

Robustness Evaluation Frameworks (42)

Multimodal Knowledge Integration (35)

Bias Detection and Mitigation (32)

Causal Reasoning Frameworks (22)

Interactive Dialogue Systems (19)

World Models with Hints of Large Language Models for Goal Achieving CogLM: Tracking Cognitive Development of Large Language Models Improving Retrospective Language Agents via Joint Policy Gradient Optimization

Hallucination Detection & Mitigation 142

Developing methods for detecting and mitigating hallucinations in generated outputs from large language models and other generative systems.

hallucination detection (2)information retrieval (1)

Sub-topics:

Dynamic Data Selection for Training (39)

Evaluation Metrics for Hallucinations (35)

Error Analysis in Multimodal Systems (30)

Contextual Relevance Assessment (21)

Bias Mitigation Techniques (17)

What the #?*!: Disentangling Hate Across Target Identities The Impact of Visual Information inChinese Characters: Evaluating Large Models’ ... Aligning Sentence Simplification withESLLearner’s Proficiency for Language Acqui...

Conversational AI for Mental Health 135

Developing conversational agents aimed at unobtrusively diagnosing mental health conditions through dialogue.

dialogue systemssymptom probingmental health diagnosisnaturalistic conversations

Sub-topics:

Multi-modal Interaction Techniques (50)

User Privacy and Ethical Considerations (41)

Bias Mitigation in AI Systems (34)

Conversational Agents for Therapy (5)

Emotionally-Aware Dialogue Systems (3)

PRACTIQ: A Practical Conversational Text-to-SQLdataset with Ambiguous and Unansw... Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Mode... Decoding Hate: Exploring Language Models’ Reactions to Hate Speech

Prompt Engineering Strategies 117

Innovative methods for crafting prompts to optimally leverage large language models for specific tasks and domains.

in-context learning (3)fine-tuning (5)

Sub-topics:

Evaluating Prompt Effectiveness (38)

Prompt Optimization for Specific Tasks (38)

Multi-modal Prompting Techniques (18)

Dynamic Prompt Adjustment (13)

Bias Mitigation through Prompting (10)

LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating... UFO: AUI-Focused Agent for WindowsOSInteraction Unmasking Implicit Bias: Evaluating Persona-PromptedLLMResponses in Power-Dispar...

Long-context Evaluation Metrics 91

Creating and assessing metrics tailored for evaluating models' performance in handling long-context inputs and generating coherent outputs.

long-context scenariosevaluation benchmarkstext generationattention visualization

Familiarity: Better Evaluation of Zero-Shot Named Entity Recognition by Quantify... Evaluating Morphological Compositional Generalization in Large Language Models Improving Data Annotation for Low-Resource Relation Extraction with Logical Rule...

Graph Representation Learning 84

Utilizing graph-based approaches for tasks such as entity disambiguation in verification processes and improving information access.

entity disambiguationinteractive graphsinformation retrievalknowledge graphs

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph ... Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Repo... Parameter-free and Accessible Prompt Learning to Enhance Adversarial Robustness ...

Language Model Quantization Techniques 37

Investigating methods for quantizing large language models to enhance performance while reducing computational costs.

model efficiencymemory optimizationquantization techniquescomputation reduction

Balancing Forget Quality and Model Utility: A ReverseKL-Divergence Knowledge Dis... AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Loc... Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring

ACL 2024

Association for Computational Linguistics 2,873 papers

+

Causal Fact Verification 256

Research focusing on verifying causal claims through the analysis of argument structures.

argument structure (1)causal reasoning (2)verification (5)

Sub-topics:

Causal Inference in Language Models (68)

Causal Relationship Extraction (49)

Benchmarking Causal Reasoning (46)

Data Quality in Causal Verification (35)

Misinformation Detection Algorithms (32)

Contradiction Detection Methods (15)

A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers o... A Data-Driven Guided Decoding Mechanism for Diagnostic Captioning A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Tech...

Data Augmentation for NLP 206

Methods to augment textual datasets for improving performance in NLP tasks using synthetic data generation.

synthetic data (5)abusive language detection (1)

Sub-topics:

Evaluation Benchmarks for Augmented Data (56)

Domain Adaptation through Augmentation (47)

Contextual Information for Data Augmentation (26)

Synthetic Data Generation Approaches (25)

Bias and Fairness Analysis in Augmentation (21)

Multimodal Data Augmentation Strategies (19)

A Collocation-based Method for Addressing Challenges in Word-level Metric Differ... A Comprehensive Evaluation of Quantization Strategies for Large Language Models A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Mode...

Causal & Emotional Attribution in Language 122

Investigating how large language models associate emotions with arbitrary words and how this aligns with human perceptions.

emotional associations (1)nonsense words (1)language models (35)

Sub-topics:

Causal Inference in Text (44)

Causal Language Modeling (44)

Sentiment Analysis Frameworks (11)

Emotion Recognition Techniques (10)

Multi-task Emotion Detection (7)

Cross-lingual Emotional Attribution (6)

A Causal Approach for Counterfactual Reasoning in Narratives A Multidimensional Framework for Evaluating Lexical Semantic Change with Social ... A Sentiment Consolidation Framework for Meta-Review Generation

Factuality and Summarization Analysis 88

Evaluating the factual accuracy of summaries generated from texts using various inference techniques.

factuality evaluation (2)summarization (7)natural language inference (1)claim extraction (1)

A Critical Study of What Code-LLMs (Do Not) Learn A Fairness Analysis of Human andAI-Generated Student Reflection Summaries A Feature-Based Approach to Annotate the Syntax ofAncientChinese

Text Generation Control 84

Techniques for generating text from large language models while maintaining control over specified attributes.

large language models (7)

A +B: A General Generator-Reader Framework for OptimizingLLMs to Unleash Synergy... A Graph per Persona: Reasoning about Subjective Natural Language Descriptions A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoni...

Cross-Modal Learning 74

Exploration of learning mechanisms that integrate information across different modalities, such as text and images.

multimodal models (2)

3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understan... A Community-Centric Perspective for Characterizing and Detecting Anti-Asian Viol... A Large Collection of Model-generated Contradictory Responses for Consistency-aw...

Few-Shot Semantic Change Detection 39

Approaches leveraging few-shot learning to detect changes in the semantics of language over time.

few-shot learning (1)semantic change (4)GPT-4 (1)

A Computational Analysis and Exploration of Linguistic Borrowings inFrench Rap L... A Context-Contrastive Inference Approach To Partial Diacritization A Course Shared Task on EvaluatingLLMOutput for Clinical Questions

Named Entity Recognition (NER) 36

Focused on improving named entity recognition tasks through novel architectures tailored for specific languages.

attention-based (1)

1024m atSMM4H2024: Tasks 3, 5 & 6 - Self Reported Health Text Classification thr... 712forTask7 at #SMM4H2024 Task 7: ClassifyingSpanish Tweets Annotated by Humans ... A Unified Generative Framework for Bilingual Euphemism Detection and Identificat...

Cognitive Modeling in Dialogue Systems 34

Research aimed at harmonizing dialogue systems with cognitive modeling to maintain character consistency during interaction.

persona integritydomain adaptationdialogue generationcognitive architecture

360∘REA: Towards A Reusable Experience Accumulation with360∘Assessment for Multi... A Comparative Analysis of Speaker Diarization Models: Creating a Dataset forGerm... A coreference corpus ofTurkish situated dialogs

Human-Like Evaluation in Translation 33

Developing methods for assessing translation quality in a manner that aligns with human judgment.

error analysistranslation evaluationprompting techniqueshuman-like

A Survey on Modelling Morality for Text Analysis A Taxonomy for Data Contamination in Large Language Models Addressing Entity Translation Problem via Translation Difficulty and Context Div...

AFA 2024

American Finance Association Annual Meeting 82 papers

+

Behavioral Preferences in Decision Making 16

This topic examines how individuals value simplicity when making economic decisions under risk.

simplicity preferencedecision under riskexperimental economicschoice behavior

Simplicity and Risk Equity Term Structures without Dividend Strips Data Bailout Stigma

Credit Market Dynamics and Leverage 14

This topic studies the relationship between broker-dealer leverage dynamics and their effect on credit supply during market disruptions.

leverage shocks (1)funding constraints (1)credit supply (1)financial stability (1)

Intermediary Leverage Shocks and Funding Conditions The Global Credit Spread Puzzle Bank Funding Risk, Reference Rates, and Credit Supply

Information Economics in Financial Markets 12

This area analyzes the interaction between information flows in financial markets and their impact on trading behaviors and asset pricing.

anomaly detectionmarket signalsinformation disseminationrisk premium

Personal Communication in an Automated World: Evidence from Loan Repayments ISSUE INFORMATION Time‐Consistent Individuals, Time‐Inconsistent Households

Asset Pricing Models and Market Performance 10

This research investigates the effectiveness of various asset pricing models in predicting credit spreads and market behavior.

credit spreadsdefault riskinvestment-grade modelsglobal markets

The Disappearing Index Effect Test Assets and Weak Factors Equilibrium Data Mining and Data Abundance

Financial Technology and Consumer Behavior 9

This research focuses on how automated financial notifications influence consumer financial behavior and reduce costs.

automatic enrollment (1)overdraft alerts (1)field experiments (1)

Sending Out an SMS: Automatic Enrollment Experiments for Overdraft Alerts A Multifactor Perspective on Volatility‐Managed Portfolios Carbon Returns across the Globe

Risk Management in Corporate Finance 9

This research evaluates the role of private equity in managing risks associated with corporate failures post-financial crisis.

private equityfailed-bank resolutionfinancial crisisrisk assessment

AMERICAN FINANCE ASSOCIATION Does Floor Trading Matter? Liquidity Transformation and Fragility in the U.S. Banking Sector

Behavioral Economics and Contract Theory 6

This research focuses on how psychological factors and strategic behavior impact contract design and incentive alignment in organizations.

principal-agent modelcontract manipulationeffort incentivesutility maximization

Scope, Scale, and Concentration: The 21^st‐Century Firm The Working Capital Credit Multiplier Capital Commitment

Consumer Debt and Labor Supply Responses 5

This topic examines how changes in mortgage payments influence household labor supply decisions and income adjustments.

mortgage payments (1)labor supply elasticity (1)

Working More to Pay the Mortgage: Household Debt, Interest Rates, and Family Lab... Presidential Address: Macrofinance and Resilience Bonds versus Equities: Information for Investment

Environmental Economics and Market Behavior 3

This area analyzes the effects of environmental pressures on corporate behavior and market dynamics in the context of pollution.

greenwashing (1)asset market (1)pollution (1)sustainability (1)

Sustainability or Greenwashing: Evidence from the Asset Market for Industrial Po... Mortgage Lock‐In, Mobility, and Labor Reallocation Half Banked: The Economic Impact of Cash Management in the Marijuana Industry

Decentralized Finance Mechanisms 2

This area explores the functioning and implications of decentralized exchanges and automated liquidity mechanisms in finance.

Uniswap (1)automated market maker (1)liquidity provision (2)Ethereum blockchain (1)

Decentralized Exchange: The Uniswap Automated Market Maker Money and Banking with Reserves and CBDC

CVPR 2024

Computer Vision and Pattern Recognition 2,716 papers

+

3D Reconstruction Techniques 240

Exploration of methods for reconstructing 3D shapes and scenes from 2D images or multi-view data.

3D reconstruction (4)keypoint detection (1)depth estimation (2)

Sub-topics:

General-Purpose 3D Neural Fields (157)

3D Point Cloud Upsampling (20)

Video-based 3D Object Detection (16)

3D Human Pose Estimation (14)

Geometric-Semantic Fusion (9)

3D Facial Expression Reconstruction (7)

2S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Re... 3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level... 3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation

Multimodal Learning Approaches 139

Methods that integrate and leverage multiple data modalities, such as images and text, for improved understanding and generation.

image captioning (1)cross-modal retrieval (1)

Sub-topics:

3D Object Detection (74)

Cross-Domain Few-Shot Segmentation (35)

Text-to-4D Scene Generation (18)

Emotion Representation and Expression Generation (5)

Audio-Visual Speech Recognition (5)

360+x: A Panoptic Multi-modal Scene Understanding Dataset 360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cro... A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames f...

Diffusion Model Architectures 131

Research focused on the development and applications of diffusion models for tasks such as image generation and editing.

diffusion models (13)image generation (4)

Sub-topics:

3D Structural Reconstruction (51)

Conditional Denoising Techniques (32)

Real-time Diffusion Sampling (20)

Joint Motion Estimation (13)

Diffusion for Video Inpainting (8)

Score Distillation in Diffusion (7)

A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Spars... A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Network ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion...

Image Restoration Techniques 115

Methods dedicated to recovering and enhancing image quality for various applications, including medical and document images.

image restoration (3)document image (1)

Sub-topics:

Image Denoising Algorithms (60)

Blind Image Super-Resolution (38)

Adaptive Deconvolution Techniques (8)

Generative Image Inpainting (5)

Spatial-Frequency Based Enhancement (4)

A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analys... A Category Agnostic Model for Visual Rearrangment A Unified Framework for Microscopy Defocus Deblur with Multi-Pyramid Transformer...

Task-Specific Prompt Engineering 78

Techniques aimed at optimizing prompts for specific machine learning tasks to enhance model performance.

prompt learning (2)text-to-image (5)few-shot learning (2)

A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation

Human Activity Recognition 70

Techniques for recognizing and understanding human behaviors and activities through video and sensor data.

human activity (1)action segmentation (1)

A Bayesian Approach to OOD Robustness in Image Classification A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection ADFactory: An Effective Framework for Generalizing Optical Flow with NeRF

Creative Video Generation 67

Innovations in generating and editing videos creatively through AI-driven methods, including sound and imagery fusion.

video editing (2)

360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion M... A Generative Approach for Wikipedia-Scale Visual Entity Recognition A Noisy Elephant in the Room: Is Your Out-of-Distribution Detector Robust to Lab...

Federated Learning Strategies 42

Researching methods and frameworks for training machine learning models across distributed devices while ensuring data privacy.

federated learning (8)

A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learn... A Versatile Framework for Continual Test-Time Domain Adaptation: Balancing Discr... AAMDM: Accelerated Auto-regressive Motion Diffusion Model

Neural Radiance Fields Development 34

Advances in neural radiance fields for rendering and representing three-dimensional scenes through neural networks.

neural radiance fields (3)

AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation Affine Equivariant Networks Based on Differential Invariants AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

Graph Neural Network Applications 20

Utilization of graph structures and neural computations for various tasks, such as ranking and learning from structured data.

graph neural networkssaliency rankingdomain separationsemantics

1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness Adaptive Slot Attention: Object Discovery with Dynamic Slot Number Adaptive Softassign via Hadamard-Equipped Sinkhorn

EACL 2024

European Chapter of ACL 791 papers

+

Sentiment Analysis in Regional Languages 188

Application of sentiment analysis techniques using sentence embeddings for Tamil and Tulu languages.

sentence embeddings (1)Dravidian languages (2)machine learning (5)

Sub-topics:

Sentiment Analysis Benchmarks (147)

Cross-Lingual Sentiment Transfer (14)

Aspect-Based Sentiment Analysis (12)

Sentiment Lexicon Development (5)

Emotion Detection in Regional Languages (5)

Multimodal Sentiment Analysis (5)

A Comparative Multidimensional Analysis of Empathetic Systems SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classificatio... Asking the Right Question at the Right Time: Human and Model Uncertainty Guidanc...

Fake News Detection 119

Utilization of a fine-tuned BERT model for detecting fake news in the Malayalam language.

multilingual modelsfine-tuned BERTsocial media analysisnatural language understanding

Sub-topics:

Multimodal Approaches to Verification (78)

Bias Analysis in News Content (23)

Stance Detection in Social Media (12)

Adversarial Training for Fake News (4)

Generating Benchmarks for Factuality Evaluation of Language Models Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-So... Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering

Knowledge Graph Completion 91

Using large language models to enhance the completion of knowledge graphs through distillation processes.

contextualization distillation (1)language models (8)

Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolutio... Parameter-Efficient Conversational Recommender System as a Language Processing T...

Contrastive Decoding Techniques 76

Mitigation of hallucinations in machine translation through innovative contrastive decoding methods.

machine translation (5)hallucinations (1)

Anisotropy Is Inherent to Self-Attention in Transformers How Transferable are Attribute Controllers on Pretrained Multilingual Translatio... MultiMUC: Multilingual Template Filling onMUC-4

Social Reasoning in Language Models 65

Investigating the capabilities of large language models in understanding and reasoning about social behavior.

neural theory of mind (1)stress testing (1)large language models (8)

Enhancing Ethical Explanations of Large Language Models through Iterative Symbol... Archer: A Human-Labeled Text-to-SQLDataset with Arithmetic, Commonsense and Hypo... Centering the Speech Community

Personalized Summarization Tools 54

Creation of a lecture summarization tool tailored for humanities students using large language models.

LLMs (5)personalization (1)

OpenPI2.0: An Improved Dataset for Entity Tracking in Texts EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Vi...

Temporal Relation Grounding 53

Research focusing on grounding temporal relations between different event spans in text.

event spans (1)

Proceedings of the 18th Conference of the European Chapter of the Association fo... Where Do We Go From Here? Multi-scale Allocentric Relational Inferencefrom Natur... Chaining Event Spans for Temporal Relation Grounding

Causal Mediation Analysis 47

Exploring causal mediation techniques to analyze and explain the dynamics of rumor detection in social contexts.

rumour detection (1)social media (1)

Bias in Opinion Summarisation from Pre-training to Adaptation: A Case Study in P... Unleashing the Power of Discourse-Enhanced Transformers for Propaganda Detection Graph-based Clustering for Detecting Semantic Change Across Time and Languages

Accent Adaptation for ASR 46

Studying adaptations in automatic speech recognition systems to generalize across diverse African accents.

zero-shot learningautomatic speech recognitionaccent recognitiontransfer learning

Language Models as Inductive Reasoners Investigating Agency ofLLMs in Human-AICollaboration Tasks SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking

Essay Scoring Methodologies 23

Development of an autoregressive approach for scoring essays based on multiple writing traits.

machine learning (1)

LLMComparative Assessment: Zero-shotNLGEvaluation through Pairwise Comparisons u... Generation-driven Contrastive Self-training for Zero-shot Text Classification wi... Quantifying the Hyperparameter Sensitivity of Neural Networks for Character-leve...

EMNLP 2024

Empirical Methods in Natural Language Processing 3,104 papers

+

User-Centric Language Model Applications 387

Creating and evaluating language model-driven tools aimed at improving usability for specific user groups, especially in education.

usabilitydigital pedagogypersonalizationuser experience

Sub-topics:

Evaluating User-Centric Tasks (99)

Knowledge Enhancement Frameworks (79)

User Instruction Understanding (50)

Cultural and Linguistic Adaptation (47)

Bias Mitigation Techniques (43)

Interactive Language Generation (27)

A Closer Look at Multidimensional Online Political Incivility A Coarse-to-Fine Prototype Learning Approach for Multi-Label Few-Shot Intent Det... A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audi...

Causal Reasoning in NLP 171

Focusing on the implementation of causal reasoning techniques in natural language processing tasks for more accurate predictions.

intent detection (1)

Sub-topics:

Applications of Causal Reasoning (118)

Evaluation Metrics for Causal Models (19)

Causal Inference Frameworks (18)

Causality Detection Techniques (13)

A Hassle-free Algorithm for Strong Differential Privacy in Federated Learning Sy... A Notion of Complexity for Theory of Mind via Discrete World Models A Novel Metric for Measuring the Robustness of Large Language Models in Non-adve...

Memory Mechanisms in Language Models 76

Investigating the nature of memorization in large language models and its implications for performance and data efficiency.

verbatim memorizationoverfittinggeneralizationmodel interpretability

A Decoding Algorithm for Length-Control Summarization Based on Directed Acyclic ... A Morphology-Based Investigation of Positional Encodings A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Lab...

Cross-Lingual Language Understanding 74

Focusing on enhancing understanding and translation capabilities across multiple languages through advanced language models.

cross-lingual (6)language modeling (1)

1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators? A Comparison of Language Modeling and Translation as Multilingual Pretraining Ob... A Multi-task Framework with Enhanced Hierarchical Attention for Sentiment Analys...

Long-Context Language Models 68

Research focused on optimizing and evaluating large language models for effective question answering over extended contexts.

question answering (3)training (3)evaluation (2)

A Learning Rate Path Switching Training Paradigm for Version Updates of Large La... A Thorough Examination of Decoding Methods in the Era ofLLMs A linguistically-motivated evaluation methodology for unraveling model’s abiliti...

Emotion Recognition in Text 59

Exploring techniques to recognize and predict emotional content in text, enhancing user interaction in conversational systems.

emotion predictionconversational contextuser-generated contentmultitask learning

A Deep Analysis of the Impact of Multiword Expressions and Named Entities onChin... A Simple and EffectiveL₂Norm-Based Strategy forKVCache Compression A SimpleLLMFramework for Long-Range Video Question-Answering

Adversarial Attacks on Language Models 46

Examining methods for conducting adversarial attacks against language models and assessing their robustness under various conditions.

robustness (2)distribution-aware (1)

A Test Suite of Prompt Injection Attacks forLLM-based Machine Translation AAVENUE: DetectingLLMBiases onNLUTasks inAAVEvia a Novel Benchmark AICCTUsystem atAVeriTeC: Re-framing automated fact-checking as a simpleRAGtask

Retrieval-Augmented Question Answering 39

Investigating retrieval-augmented methodologies to elevate the performance of question answering systems, specifically in complex queries.

retrieval systemsmulti-hop reasoningefficient inferenceQ&A systems

AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings ARM: An Alignment-and-Replacement Module forChinese Spelling Check Based onLLMs ASTE-Transformer: Modelling Dependencies in Aspect-Sentiment Triplet Extraction

Language Model Distillation 35

Researching methods to streamline the capabilities of language models through distillation techniques to improve their efficiency and performance.

knowledge distillation (2)

A Novel Instruction Tuning Method forVietnamese Mathematical Reasoning using Tra... AHP-PoweredLLMReasoning for Multi-Criteria Evaluation of Open-Ended Responses Aligners: DecouplingLLMs and Alignment

Multimodal Historical Analysis 13

Developing models that combine visual and textual information to enhance analysis and understanding of historical events.

multi-modal (1)dynamic emulation (1)historical battles (1)

***YesBut***: A High-Quality Annotated Multimodal Dataset for evaluating Satire ... A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language M... AlanaVLM: A Multimodal EmbodiedAIFoundation Model for Egocentric Video Understan...

ICAIF 2024

ACM International Conference on AI in Finance 99 papers

+

Fraud Detection Techniques 15

Research focused on developing and evaluating methods to detect fraudulent activities in financial transactions.

transaction fraud (1)fraud models (1)bias audits (1)fairness metrics (1)

Graph Feature Preprocessor: Real-time Subgraph-based Feature Extraction for Fina... WallStreetFeds: Client-Specific Tokens as Investment Vehicles in Federated Learn... Extracting Alpha from Financial Analyst Networks

Financial Time Series Forecasting 14

Developing algorithms and models to predict financial metrics and trends based on historical time series data.

temporal graphsconditional GANsexplainable modelsstock predictions

Contrastive Learning of Asset Embeddings from Financial Time Series Modality-aware Transformer for Financial Time series Forecasting The Effect of Liquidity on the Spoofability of Financial Markets

Large Language Models in Finance 12

Utilizing large language models for analysis and comprehension of financial data, improving decision-making processes.

neural bandits (1)

ECC Analyzer: Extracting Trading Signal from Earnings Conference Calls using Lar... Online Personalizing White-box LLMs Generation with Neural Bandits Enhancing Financial Question Answering with a Multi-Agent Reflection Framework

Simulations of Financial Systems 11

Creating models that simulate financial environments to study behaviors and outcomes of various economic factors.

economic impact (1)

Simulate and Optimise: A two-layer mortgage simulator for designing novel mortga... Simulating the Economic Impact of Rationality through Reinforcement Learning and... Tax Credits and Household Behavior: The Roles of Myopic Decision-Making and Liqu...

Reinforcement Learning in Finance 11

Exploring the application of reinforcement learning methodologies to model and optimize financial strategies.

agent-based modelingmortgage simulatorrisk-based controlportfolio optimization

Open Set Recognition for Random Forest Rolling Forward: Enhancing LightGCN with Causal Graph Convolution for Credit Bon... Cluster-driven Hierarchical Representation of Large Asset Universes for Optimal ...

Adaptive Learning Strategies 8

Studying adaptive algorithms that learn and optimize strategies based on evolving data within financial contexts.

neural architecturelearning approachesdynamic adaptationssequential predictions

Adaptive Risk-Based Control in Financial Trading DySTAGE: Dynamic Graph Representation Learning for Asset Pricing via Spatio-Temp... Unveiling Recurring Financial Patterns: Novel unsupervised filtering algorithms ...

Unsupervised Learning in Finance 8

Investigating unsupervised techniques to reveal insights and structure within financial data without predefined labels.

clustering algorithmsalpha extractionfinancial patternsoutlier detection

Can an unsupervised clustering algorithm reproduce a categorization system? Why Groups Matter: Necessity of Group Structures in Attributions Autoregressive DRL with Learned Intrinsic Rewards for Portfolio Optimisation

Automated Market Making 7

Research on techniques to optimize market making processes and enhance liquidity in financial systems.

beta policies (1)linear programming (1)financial options (1)liquidity (1)

Market Making with Learned Beta Policies Designing Expressive and Liquid Financial Options Markets via Linear Programming... Detecting Collective Liquidity Taking Distributions

Quantitative Risk Management 6

Applying quantitative techniques to assess and manage risk in trading and investment scenarios.

quadratic variation (1)

Data-driven Derivative Hedging with Quadratic Variation Penalty NeuralFactors: A Novel Factor Learning Approach to Generative Modeling of Equiti... Simulating Asset Prices using Conditional Time-Series GAN

Graph Neural Networks in Finance 6

Employing graph neural network architectures to analyze relationships in financial datasets for various applications.

dynamic graphsportfolio constructionfraud detectionasset pricing

FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Condition... AI versus AI in Financial Crimes & Detection: GenAI Crime Waves to Co-Evolut... Transforming Unstructured Sensitive Information into Structured Knowledge

ICML 2024

International Conference on Machine Learning 2,610 papers

+

Reinforcement Learning & Transfer Learning 405

This topic covers the integration of reinforcement learning techniques with transfer learning principles to improve adaptability.

policy optimization (5)dynamics shifts (1)continual learning (8)

Sub-topics:

Sample Efficiency in RL (270)

Exploration Strategies in RL (36)

Reward Shaping Techniques (25)

Transfer Learning in Deep RL (21)

Multi-Agent Reinforcement Learning (18)

Policy Gradient Algorithms (14)

BeigeMaps: Behavioral Eigenmaps for Reinforcement Learning from Images Learning to Play Atari in a World of Tokens Probabilistic Generating Circuits - Demystified

Statistical Model Discovery Using Language Models 332

This research focuses on leveraging language models for automatic discovery and interpretation of statistical models.

language models (40)

Sub-topics:

Dynamic Representation Learning (102)

Robustness to Distribution Shifts (50)

Efficient Fine-tuning Techniques (43)

Integration of Graph Structures (39)

Bias Detection in Models (34)

Uncertainty Estimation Methods (30)

Revisiting Character-level Adversarial Attacks for Language Models InferCept: Efficient Intercept Support for Augmented Large Language Model Infere... A Unified Framework for Learning with Nonlinear Model Classes from Arbitrary Lin...

Self-Supervised Learning Paradigms 319

This research explores self-supervised learning methodologies to enhance feature extraction across different domains.

contrastive learning (5)

Sub-topics:

Unsupervised Learning Frameworks (105)

Robustness in Self-Supervised Models (74)

Feature Representation Learning (52)

Graph Neural Network Paradigms (31)

Next-Token Prediction Challenges (24)

Causal Inference in Self-Supervised Learning (19)

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers FrameQuant: Flexible Low-Bit Quantization for Transformers Improved Differentially Private and Lazy Online Convex Optimization: Lower Regre...

Causal Inference in Image Quality 279

This research focuses on utilizing causal inference techniques to enhance image quality assessment metrics.

Causal-IQA (1)image quality assessment (2)causal inference (5)generalization (7)

Sub-topics:

Causal Inference Algorithms (203)

Causal Models for Image Processing (24)

Bias and Fairness in Image Quality (18)

Interpretable Causal Inference in Imaging (12)

Image Quality Assessment Metrics (10)

Data Augmentation Techniques for Causality (8)

How to Escape Sharp Minima with Random Perturbations In-Context Language Learning: Architectures and Algorithms Robust and Conjugate Gaussian Process Regression

Graph Neural Networks for Structured Data 278

This work develops graph neural network techniques tailored for aggregate representations of molecular structures.

E(3)-invariancemolecular conformersaggregation networksgraph-based learning

Sub-topics:

Graph-based Representation Learning (71)

Graph Neural Network Architectures (65)

Robustness in Graph Learning (45)

Graph Neural Networks for Reinforcement Learning (36)

Graph-based Active Learning (30)

Interpretability of Graph Neural Networks (15)

Optimal Coresets for Low-Dimensional Geometric Median OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language M... Revisiting Inexact Fixed-Point Iterations for Min-Max Problems: Stochasticity an...

Fairness and Bias in Machine Learning 239

This research investigates methods for identifying and mitigating biases in machine learning systems to promote fairness.

intersectional unfairness (1)

Sub-topics:

Evaluation of Model Bias (98)

Standardized Fairness Measures (56)

Non-Markovian Fairness Approaches (30)

Fairness in Sequential Decision Making (18)

Adversarial Attacks on Fairness (11)

Disparities in Feature Importance (10)

LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tas... Policy Evaluation for Variance in Average Reward Reinforcement Learning Distinguishing the Knowable from the Unknowable with Language Models

Adaptive Strategies in Simulation Environments 203

This topic focuses on developing adaptive learning strategies for optimizing policy performance in complex simulation settings.

policy optimization (1)reinforcement learning (2)

Sub-topics:

Dynamic Resource Allocation Techniques (68)

Robustness Benchmarking Frameworks (33)

Adaptive Learning Rate Strategies (27)

Causal Discovery in Simulated Environments (20)

Behavioral Diversity in Reinforcement Learning (18)

Simulation Robustness Analysis (13)

Adaptively Perturbed Mirror Descent for Learning in Games The Non-linear F-Design and Applications to Interactive Learning Improving Computational Complexity in Statistical Models with Local Curvature In...

Diffusion Model Architectures 195

This area explores the theoretical and practical advancements in the architectures and applications of diffusion models.

Gaussian processes (1)inverse problems (3)

Sub-topics:

Applications of Diffusion Models (149)

Neural Diffusion Models (26)

Uncertainty Estimation in Diffusion (14)

Iterated Denoising Strategies (3)

Comparative Benchmarking of Diffusion Techniques (3)

Learning the Target Network in Function Space Translation Equivariant Transformer Neural Processes Simulation of Graph Algorithms with Looped Transformers

Unsupervised Time Series Anomaly Detection 189

This topic explores advancements and challenges in unsupervised methods for detecting anomalies in time series data.

anomaly detection (3)time series (11)robustness (2)algorithms (1)

Sub-topics:

Representation Learning for Time Series (72)

Anomaly Detection Algorithms (42)

Dimensionality Reduction Techniques (29)

Evaluation Metrics for Anomaly Detection (25)

Multi-Modal Time Series Analysis (20)

Discovering Bias in Latent Space: An Unsupervised Debiasing Approach REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Upda... A Rate-Distortion View of Uncertainty Quantification

Weakly Supervised Drug Response Prediction 98

This area investigates using weakly supervised learning models to improve predictions of drug response in cancer treatment.

representation learning (1)

Balancing Feature Similarity and Label Variability for Optimal Size-Aware One-sh... Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning CosPGD: an efficient white-box adversarial attack for pixel-wise prediction task...

NAACL 2024

North American Chapter of ACL 1,582 papers

+

Instruction Tuning & Alignment 363

Research focusing on the tuning and alignment of language models for specific tasks or multilingual contexts.

fine-tuning (8)prompt engineering (1)multilingual instruction (1)

Sub-topics:

Robustness in Instruction Tuning (96)

Evaluation Benchmarks for Instruction Tuning (68)

Data Augmentation for Instruction Tuning (51)

Cross-Lingual Alignment Techniques (49)

Dialogue and Conversational Adaptation (41)

Instruction-Tuned Multimodal Models (21)

Proceedings of the 2024 Conference of the North American Chapter of the Associat... Assessing Logical Puzzle Solving in Large Language Models: Insights from a Mines... Effective and Efficient Conversation Retrieval for Dialogue State Tracking with ...

Generative Forecasting Models 270

Investigating generative models for forecasting tasks based on temporal data represented in knowledge graphs.

forecasting (1)large language models (35)

Sub-topics:

Task-Specific Generative Applications (67)

Generative Text Modeling (52)

Evaluation of Generative Outputs (40)

Data Augmentation for Generative Models (35)

Improving Robustness in Generation (27)

Bias in Generative Models (21)

Text Diffusion Model with Encoder-Decoder Transformers for Sequence-to-Sequence ... Extractive Summarization with Text Generator Self-generated Replay Memories for Continual Neural Machine Translation

Causal Inference in NLP 191

Investigating causal relationships in natural language processing tasks, particularly in human-interactive settings.

human-language collaborationcausal reasoningcausal modelsinference methods

Sub-topics:

Causal Models for Language Understanding (95)

Causal Impact of Training Data (41)

Causal Benchmarks for Model Evaluation (27)

Bias Mitigation in NLP Models (22)

Counterfactual Reasoning in NLP (6)

Promptly Predicting Structures: The Return of Inference On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from... FPT: Feature Prompt Tuning for Few-shot Readability Assessment

Bias Detection & Mitigation 178

Studying the biases present in AI models and methodologies for detecting and mitigating these biases.

fairness (6)de-biasing (1)

Sub-topics:

Evaluating Bias in LLM Outputs (106)

Fairness in Data Annotation (29)

Cultural Sensitivity in AI Models (19)

Adversarial Techniques for Bias Detection (12)

Counterfactual Data Augmentation (9)

Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revisi... LLMs Are Few-Shot In-Context Low-Resource Language Learners AMRFact: Enhancing Summarization Factuality Evaluation withAMR-Driven Negative S...

Clinical NLP Applications 106

Research on employing NLP techniques in clinical settings, such as coding and summarizing medical records.

clinical codingabstractive summarizationmedical NLPautomated systems

Sub-topics:

Knowledge Distillation Techniques (41)

Robustness in Medical NLP (28)

Automated Evaluation Frameworks (17)

Conversational Agents for Health (10)

Multimodal Processing in Healthcare (10)

Named Entity Recognition Under Domain Shift via Metric Learning for Life Science... Strings from the Library ofBabel: Random Sampling as a Strong Baseline for Promp... The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human ...

Multimodal Emotion Analysis 105

Analysis of emotions in conversations using multiple modalities, including text and audio signals.

emotion recognition (4)emotion cause analysis (2)

Sub-topics:

Multimodal Data Fusion Techniques (34)

Contextual Emotion Detection (25)

Emotion Classification Benchmarks (21)

Cultural and Linguistic Variations in Emotion (17)

Emotion Recognition in Dialogue (8)

TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conv... MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tunin... DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue D...

Hierarchical Text Classification 83

Developing neural network architectures focused on classifying texts into a structured hierarchy of labels.

multilabel classificationRNNsneural networkshierarchical models

Simple and effective data augmentation for compositional generalization FLAP: Flow-Adhering Planning with Constrained Decoding inLLMs E5: Zero-shot Hierarchical Table Analysis using AugmentedLLMs via Explain, Extra...

Fact-Checking & Trustworthiness 81

Creating methodologies to ensure factual consistency and trustworthiness in statements generated by AI models.

fact-checking modulesgrounded reasoningtrustworthy AIsemantic verification

An Interactive Framework for Profiling News Media Sources VertAttack: Taking Advantage of Text Classifiers’ Horizontal Vision Dial-MAE:ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems

Role of Semantic Representations 72

Exploring how semantic representations influence the performance of large language models in NLP tasks.

large language models (9)

Building Knowledge-Guided Lexica to Model Cultural Variation Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)?A.K.A. WillLLMs... Causal Inference for Human-Language Model Collaboration

Knowledge Graph Integration 53

Utilizing knowledge graphs to enhance question answering and reasoning capabilities in AI systems.

semantic pruning (1)question answering (4)knowledge graphs (2)

kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbo... ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models Visual Grounding Helps Learn Word Meanings in Low-Data Regimes

NeurIPS 2024

Neural Information Processing Systems 4,494 papers

+

Optimization Techniques for Learning 179

Methods and frameworks focused on optimizing machine learning algorithms, enhancing both convergence rates and learning efficacy.

Minimax Optimization (2)Bayesian Optimization (2)

Sub-topics:

Robustness in Learning Algorithms (48)

Continuous and Online Learning (46)

Gradient-Based Optimization Methods (39)

Hyperparameter Optimization Strategies (24)

Multi-Objective Optimization Frameworks (13)

Bayesian Optimization Techniques (9)

-DPO: Direct Preference Optimization with Dynamic P²: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scali... -Softmax: Approximating One-Hot Vectors for Mitigating Label Noise

Image Generation & Synthesis 154

Techniques that concentrate on generating and synthesizing images and video from various inputs, including 3D models and video diffusion.

3D Model AnimationSparse View SynthesisOccluded Pose EstimationDeepfake Detection

Sub-topics:

Benchmarking Image Generation Models (90)

3D Scene Generation Techniques (20)

Diffusion Models for Image Synthesis (8)

Language-Guided Image Generation (6)

Image Super-Resolution Approaches (3)

C²M³: Cycle-Consistent Multi-Model Merging E³: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset SE(3) Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation

Causal Inference Strategies 153

Techniques for identifying causal relationships and effects in complex data settings, especially involving latent structures and sequential decision processes.

Marginal Structural Models (1)Latent Variables (1)

Sub-topics:

Benchmarking Causal Methods (63)

Robustness in Causal Inference (39)

Causal Graph Learning (22)

Causal Sequence Modeling (20)

Interventional Fairness Strategies (8)

3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D... 4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on RD... 4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities

Neural Program Learning 89

Focus on techniques that leverage neural networks to learn and synthesize programs to improve data efficiency in machine learning tasks.

Data EfficiencyNeural ComputationProgram SynthesisLearning to Learn

A Bayesian Approach for Personalized Federated Learning in Heterogeneous Setting... A Canonicalization Perspective on Invariant and Equivariant Learning A Foundation Model for Zero-shot Logical Query Reasoning

Large Scale Benchmarking 71

Establishment of comprehensive benchmarks for evaluating model performance across a variety of human-centric tasks and datasets.

Human-Centric (1)Referring Expression (1)

²DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchma... Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild... 4+3 Phases of Compute-Optimal Neural Scaling Laws

Graph-Based Learning Techniques 67

Explores methodologies that utilize graph structures for various learning tasks, focusing on improving analytical capabilities in complex relational data.

Graph Neural NetworksProfessional AnalysisKnowledge GraphsGraph Embeddings

NeuroPath: A Neural Pathway Transformer for Joining the Dots of Human Connectome... A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point... A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph...

Uncertainty Quantification Approaches 63

Research aimed at quantifying and managing uncertainty in predictive models and ensuring robust decision-making in uncertain environments.

Deep Ensembles (1)Confidence Calibration (1)

2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extre...

Diffusion Model Architectures 60

Research focusing on the design and optimization of models that utilize diffusion processes for various tasks including generation and knowledge distillation.

Denoising (1)

ID³: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Rec... (FL)²: Overcoming Few Labels in Federated Semi-Supervised Learning A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimat...

Time Series Analysis Techniques 60

Methods specifically designed to analyze and predict outcomes in time-dependent data, addressing both stationary and non-stationary challenges.

Forecasting (6)Dynamic Normalization (1)Segmentation (1)

A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Mis... APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores... Absorb & Escape: Overcoming Single Model Limitations in Generating Heterogeneous...

Federated Learning Methodologies 47

Innovative approaches to federated learning that enhance privacy and performance in settings with limited labeled data and diverse objectives.

Privacy-PreservingFew-Shot LearningDecoupled Task-AgnosticDistributed Training

ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in... pfl-research: simulation framework for accelerating research in Private Federate... 2D-OOB: Attributing Data Contribution Through Joint Valuation Framework

ACL 2023

Association for Computational Linguistics 3,203 papers

+

Transformers for Sequential Tasks 282

Exploration of transformer models' ability to comprehend and execute sequential instructions in various domains.

sequence-to-sequence (1)transformer architecture (1)natural language processing (1)

Sub-topics:

Robustness Evaluation in NLP (56)

Sequence-to-Sequence Learning (49)

Zero-Shot Language Processing (40)

Multi-Modal Learning Approaches (31)

Knowledge Distillation Techniques (30)

Emotion Recognition in Dialogues (29)

2*nis better thann2: Decomposing Event Coreference Resolution into Two Tractable... A Better Way to Do Masked Language Model Scoring A Cautious Generalization Goes a Long Way: Learning Morphophonological Rules

Dialogue Systems Evaluation 145

Investigation of methodologies to evaluate dialogue systems, particularly through the development of novel metrics like dialogue density.

open-domain dialogues (1)

Sub-topics:

Error Analysis in Dialogue Systems (42)

Benchmarking Dialogue System Performance (42)

User-Centric Evaluation Approaches (34)

Evaluation Metrics for Dialogue Systems (20)

Long-form Dialogue Evaluation (7)

A Call for Standardization and Validation of Text Style Transfer Evaluation A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for E... A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity...

Few-Shot Learning Approaches 101

Explores few-shot learning techniques that utilize minimal labeled data, leveraging adversarial cues to improve learning outcomes.

adversarial knowledge (1)contrastive prompting (1)language learners (1)

Sub-topics:

Benchmarking Few-Shot Learning Techniques (33)

Few-Shot Transfer Learning Approaches (32)

Evaluation Metrics for Few-Shot Learning (14)

Zero-Shot and Few-Shot Learning (12)

Meta-Learning for Few-Shot Tasks (10)

A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed M... A Class-Rebalancing Self-Training Framework for Distantly-Supervised Named Entit... A Critical Evaluation of Evaluations for Long-form Question Answering

Knowledge-Based Question Answering 92

Development of systems that answer questions based on a structured knowledge base while using computational approaches for reasoning.

knowledge base (2)question answering (12)program induction (1)space debris (1)

(QA)2: Question Answering with Questionable Assumptions A Cross-Modality Context Fusion and Semantic Refinement Network for Emotion Reco... A Hierarchical Explanation Generation Method Based on Feature Interaction Detect...

Spurious Correlations Mitigation 85

Techniques to identify and mitigate unintended correlations in machine learning models, particularly in text-based applications.

text classificationspurious correlationdata biasresilience strategies

A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Lan... A Dataset of Argumentative Dialogues on Scientific Papers A Language-First Approach for Procedure Planning

Emotion Recognition in Texts 79

Methods for identifying emotions in mixed-language text messages, leveraging tuning techniques to improve classification accuracy.

code-mixed languagesoft prompt tuningtext emotion classificationlinguistic features

A Comparative Analysis of the Effectiveness of Rare Tokens on Creative Expressio... A Fast Algorithm for Computing Prefix Probabilities A Fine Line Between Irony and Sincerity: Identifying Bias in Transformer Models ...

Cross-Lingual Knowledge Transfer 67

Research methods aimed at transferring knowledge across different languages using multilingual models, particularly in resource-limited contexts.

cross-lingual transfer (3)low-resource languages (2)knowledge distillation (2)

A Comparative Study on the Impact of Model Compression Techniques on Fairness in... A Holistic Approach to Reference-Free Evaluation of Machine Translation A New Aligned SimpleGerman Corpus

Multimodal Summarization Techniques 60

Research on methods that integrate and summarize information from multiple modalities, such as text and images or audio.

coarse-to-fine approachmultimodal datacontent summarizationvisual-audio inputs

A Dataset for Explainable Sentiment Analysis in theGerman Automotive Industry A Dataset for Physical and Abstract Plausibility and Sources of Human Disagreeme... A Match Made in Heaven: A Multi-task Framework for Hyperbole and Metaphor Detect...

Explainable AI in Sentiment Analysis 29

Focuses on developing sentiment analysis models that provide understandable explanations for their predictions to enhance user trust.

explainable modelssentiment interpretationautomotive industryuser trust

A Compare-and-contrast Multistage Pipeline for Uncovering Financial Signals in F... A Gradient Control Method for Backdoor Attacks on Parameter-Efficient Tuning ACSMKRHRatSemEval-2023 Task 10: Explainable Online Sexism Detection(EDOS)

Adversarial Training for NLP 28

Research focused on improving natural language processing models by training them against adversarial examples to enhance stability.

robustness (1)

A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion R... A Robust Information-Masking Approach for Domain Counterfactual Generation A Static Evaluation of Code Completion by Large Language Models

AFA 2023

American Finance Association Annual Meeting 84 papers

+

Financial Market Communication 24

Analysis of how communication strategies in financial markets can lead to information black holes and affect project financing.

information asymmetryfinancial disclosuresrisk communicationmarket reactions

Prestige, Promotion, and Pay Aversion to Student Debt? Evidence from Low‐Wage Workers Auctions with Endogenous Initiation

Complex Models in Finance 21

This research studies the advantages of using complex models over simple models for predicting market returns.

return predictability (1)market returns (1)

The Virtue of Complexity in Return Prediction Information Cascades and Threshold Implementation: Theory and an Application to ... ISSUE INFORMATION

Insider Trading Dynamics 8

An analysis of how legal risks influence the trading behavior of insiders, particularly after regulatory shocks.

legal risk (1)insider trading (1)

Legal Risk and Insider Trading Disclosing to Informed Traders Attention Spillover in Asset Pricing

Behavioral Biases in Trading 8

Research into how cognitive biases and heuristics influence the trading decisions and performance of institutional investors.

heuristicsinstitutional investorsbuying behaviorselling performance

Trading and Shareholder Democracy Financing the Gig Economy Operating Hedge and Gross Profitability Premium

Impact of News Positioning 6

An examination of how the positioning of financial news affects market reactions and price movements.

excess returns (1)

The Global Impact of Brexit Uncertainty Liquidation Value and Loan Pricing Interest Rate Skewness and Biased Beliefs

Entrepreneurial Financing Trends 6

Study of the effectiveness of angel investor tax credits in fostering entrepreneurial growth across states.

angel investor tax creditsentrepreneurshipstate-level analysisventure capital

Intervention with Screening in Panic‐Based Runs AMERICAN FINANCE ASSOCIATION Entrepreneurial Wealth and Employment: Tracing Out the Effects of a Stock Market...

Yield Curve Control Analysis 4

This topic focuses on the impact and effectiveness of yield curve control measures in addressing economic challenges, using case studies like Australia.

quantitative easing (1)yield curve control (1)

The Narrow Channel of Quantitative Easing: Evidence from YCC Down Under Household Liquidity Constraints and Labor Market Outcomes: Evidence from a Danis... Global Pricing of Carbon‐Transition Risk

Option Trading Strategies 3

Investigation into the performance of options investments based on historical return patterns across different equities.

trading performance (1)

Discount Rates, Debt Maturity, and the Fiscal Theory Retail Trading in Options and the Rise of the Big Three Wholesalers Selling Fast and Buying Slow: Heuristics and Trading Performance of Institutiona...

Shareholder Voting Mechanisms 2

Exploration of how trading activities shape shareholder voting outcomes and the implications for market governance.

shareholder democracyvoting behaviortrading effectsmarket structure

Front‐Page News: The Effect of News Positioning on Financial Markets Optimal Sequential Selling Mechanism and Deal Protections in Mergers and Acquisi...

AI Talent Migration Impact 1

Research on how the migration of AI talent from universities affects entrepreneurial activity and startup funding in affected regions.

brain drain (1)entrepreneurship (1)

Artificial Intelligence, Education, and Entrepreneurship

CVPR 2023

Computer Vision and Pattern Recognition 2,353 papers

+

Robustness and Generalization 187

Research aimed at enhancing the performance and reliability of models in the presence of adversarial conditions.

architectural design (1)cross-modal retrieval (1)domain adaptation (3)robust generalization (2)

Sub-topics:

Generalization in Few-Shot Learning (58)

Domain Adaptation Strategies (52)

Adversarial Robustness Techniques (38)

Robustness in Semantic Segmentation (27)

Test-Time Adaptation Approaches (12)

3Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition A Bag-of-Prototypes Representation for Dataset-Level Applications A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation

Point Cloud Processing 165

Techniques aimed at improving and manipulating point cloud data for various applications.

point cloud (13)

Sub-topics:

Point Cloud Analysis (135)

Point Cloud Segmentation (12)

3D Shape Reconstruction (10)

Geometric Feature Extraction (4)

2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adap... 3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions 3D Line Mapping Revisited

Image Segmentation Techniques 149

Methods focusing on accurately delineating regions or objects within images.

saliency prompt (1)

Sub-topics:

Unsupervised Domain Adaptation for Segmentation (51)

3D Shape Reconstruction Techniques (46)

Active Learning for Segmentation (34)

Video Instance Segmentation (10)

Medical Image Segmentation (5)

Few-Shot Semantic Segmentation (3)

1% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions A Simple Framework for Text-Supervised Semantic Segmentation A Soma Segmentation Benchmark in Full Adult Fly Brain

Knowledge Transfer in Machine Learning 134

Techniques that enable models to effectively transfer knowledge from one task or domain to another.

incremental learning (2)knowledge distillation (5)class attention transfer (1)domain adaptation (4)

Sub-topics:

Multi-Modal Knowledge Integration (58)

Domain Adaptation Techniques (37)

Knowledge Distillation Approaches (16)

Lifelong Learning Strategies (15)

Zero-Shot Learning Frameworks (8)

(ML)²P-Encoder: On Exploration of Channel-Class Correlation for Multi-Label Zero... A Meta-Learning Approach to Predicting Performance and Data Requirements A New Benchmark: On the Utility of Synthetic Data With Blender for Bare Supervis...

Multimodal Representation Learning 107

Approaches to learning interactions and representations that involve multiple data modalities like text and images.

vision-language (5)cross-modal (3)embedding (2)contrastive learning (3)

Sub-topics:

3D Shape Reconstruction (47)

Multimodal Action Recognition (29)

Human Pose Estimation (14)

Video Frame Interpolation (12)

Vision-Language Navigation (5)

"Seeing" Electric Network Frequency From Events 1000 FPS HDR Video With a Spike-RGB Hybrid Camera 3D Cinemagraphy From a Single Image

Human Pose Estimation 58

Research focusing on techniques for estimating human poses from images or videos.

bottom-up (1)anchor-to-joint (1)

3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels 3D Human Mesh Estimation From Virtual Markers 3D Human Pose Estimation With Spatio-Temporal Criss-Cross Attention

Generative Adversarial Networks (GANs) 51

Utilization of GAN architectures for generating and transforming images with high fidelity.

feature fusion (1)virtual re-staining (1)image synthesis (2)

3D GAN Inversion With Facial Symmetry Prior 3D-Aware Face Swapping 3D-Aware Facial Landmark Detection via Multi-View Consistent Training on Synthet...

Diffusion Models 47

Research on diffusion-based generative models that transform inputs into detailed outputs like images and videos.

video editing (1)3D-aware (1)

3D Registration With Maximal Cliques AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training Align Your Latents: High-Resolution Video Synthesis With Latent Diffusion Models

Temporal Action Localization 45

Methods that identify and classify actions in video sequences over time.

event perceptionweak supervisiontemporal groundingaction recognition

3D Video Object Detection With Learnable Object-Centric Global Optimization A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift A Unified Pyramid Recurrent Network for Video Frame Interpolation

Face Recognition & Forgery Detection 28

Techniques for identifying and verifying human faces, as well as detecting manipulated images.

action units (1)forgery detection (1)

AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object ... AUNet: Learning Relations Between Action Units for Face Forgery Detection Aligning Bag of Regions for Open-Vocabulary Object Detection

EACL 2023

European Chapter of ACL 729 papers

+

Document Processing & Summarization 140

Focusing on techniques for linking documents and generating summaries from complex textual sources.

question generation (2)

Sub-topics:

Event Extraction and Tracking (52)

Data Augmentation for Summarization (32)

Constructing Domain-Specific Summarization Benchmarks (20)

Evaluating Summary Quality (16)

Abstractive Summarization Techniques (13)

Multimodal Document Processing (7)

Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centr... Exploiting Summarization Data to Help Text Simplification Shortcomings of Question Answering Based Factuality Frameworks for Error Localiz...

Low-Resource Language Processing 109

Developing techniques and frameworks for natural language processing and machine translation in low-resource languages.

indigenous languages (1)

Sub-topics:

Cross-Lingual Transfer Learning (31)

Evaluation Frameworks for Low-Resource NLP (23)

Data Augmentation Techniques (23)

Zero-Shot Learning Approaches (14)

Addressing Class Imbalance (9)

Multilingual Representation Learning (9)

Shironaam:Bengali News Headline Generation using Auxiliary Information Investigating data partitioning strategies for crosslinguistic low-resourceASRev... UScore: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machi...

Language Model Evaluation & Bias 98

Researching methods to evaluate and measure biases in language models using statistical and demographic data.

bias evaluation (2)descriptive bias (1)

Proceedings of the 17th Conference of the European Chapter of the Association fo... A Two-Sided Discussion of Preregistration ofNLPResearch Sentiment as an Ordinal Latent Variable

Dialogue System Development 85

Creating advanced dialogue systems that track states and enhance interaction quality using various contextual techniques.

dialogue state tracking (3)persona-grounded dialogue (1)schema-guided dialogue (1)

Socratic Question Generation: A Novel Dataset, Models, and Evaluation CHARD: Clinical Health-Aware Reasoning Across Dimensions for Text Generation Mod... Assistive Recipe Editing through Critiquing

Multi-Task Learning & Transfer Learning 66

Exploring models that leverage multitasking and transfer learning to enhance performance across various NLP tasks.

parameter-efficient tuning (1)domain adaptation (1)

Do we need Label Regularization to Fine-tune Pre-trained Language Models? Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies PANCETTA: Phoneme Aware Neural Completion to Elicit Tongue Twisters Automaticall...

Commonsense Knowledge Integration 57

Integrating commonsense knowledge into machine learning models to improve reasoning and contextual understanding.

knowledge graphs (1)

PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search WinoDict: Probing language models for in-context word acquisition Understanding Transformer Memorization Recall Through Idioms

Entity Disambiguation & Identification 49

Developing models and methods to accurately identify and disambiguate entities within text and news articles.

entity definitions (1)entity recognition (2)

Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research ... Aggregating Crowdsourced and Automatic Judgments to Scale Up a Corpus of Anaphor... Efficient Hybrid Generation Framework for Aspect-Based Sentiment Analysis

Text Augmentation Techniques 45

Investigating methods for augmenting text data to bolster training effectiveness and model robustness.

data augmentation (6)Levenshtein prediction (1)context-aware (1)

PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data... FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric Friend-training: Learning from Models of Different but Related Tasks

Phonological & Lexical Analysis 30

Conducting analyses that explore the phonological and lexical aspects of languages, focusing on historical and cross-lingual data.

phonological ontology (1)language history (1)

“John is 50 years old, can his son be 65?” EvaluatingNLPModels’ Understanding of... On the Intersection of Context-Free and Regular Languages Improving Sign Recognition with Phonology

Skill Classification with Graphs 5

Utilizing graph neural networks to classify job skills from complex and diverse job descriptions.

extreme multi-label classification (1)graph neural networks (2)job skills (1)

Event Temporal Relation Extraction withBayesian Translational Model Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks MetaQA: Combining Expert Agents for Multi-Skill Question Answering

EMNLP 2023

Empirical Methods in Natural Language Processing 2,932 papers

+

Language Model Evaluation 262

This topic addresses the methods and metrics for assessing the performance and fairness of language models.

quality metrics (1)reference-free metrics (1)

Sub-topics:

Evaluation Metrics for Language Models (114)

Contextual Understanding Assessment (46)

Bias Mitigation Techniques (31)

Evaluation of Multimodal Integration (27)

Human-Like Responses Evaluation (26)

Instruction Tuning Effects (11)

4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees 90% F1 Score in Relation Triple Extraction: Is it Real? A Benchmark for Evaluating Machine Translation Metrics on Dialects without Stand...

Data Augmentation Techniques 141

This research concentrates on enhancing training datasets to improve model robustness and performance through various augmentation strategies.

adversarial sample generation (1)data factors (1)noise learning (1)

Sub-topics:

Data Efficiency Strategies (83)

Domain Adaptation Methods (22)

Knowledge Distillation Approaches (17)

Active Learning Frameworks (15)

Prompt Tuning Techniques (4)

A Diachronic Perspective on User Trust inAIunder Uncertainty A Multi-Modal Multilingual Benchmark for Document Image Classification A Parallel Corpus forVietnamese Central-Northern Dialect Text Transfer

Text Generation Techniques 120

This area encompasses the development of methods and models specifically aimed at generating coherent and contextually relevant text.

data-to-text generation (1)text-to-SQL (2)

Sub-topics:

Evaluation Metrics for Generative Models (47)

Neural Network Architectures for Text Generation (44)

Multi-Modal Text Generation (16)

Controllable Text Generation (7)

Dialogue Generation in AI (6)

1-PAGER: One Pass Answer Generation and Evidence Retrieval A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generatio... A Cheaper and Better Diffusion Language Model with Soft-Masked Noise

Zero-Shot Learning 98

This area investigates the capability of models to make predictions or perform tasks without prior specific training data for those tasks.

generalization (5)

2INER: Instructive and In-Context Learning on Few-Shot Named Entity Recognition A Boundary Offset Prediction Network for Named Entity Recognition A Critical Analysis of Document Out-of-Distribution Detection

Causal Reasoning & Analysis 85

This topic delves into understanding and modeling causal relationships in data, especially for applications in natural language processing.

event extraction (3)corporate performance changes (1)causal rationale (1)

A Benchmark for Reasoning with Spatial Prepositions A Dataset for Investigating the Impact of Context for Offensive Language Detecti... A Fine-Grained Taxonomy of Replies to Hate Speech

Prompt Engineering 70

This topic focuses on techniques for crafting and optimizing prompts to improve the performance of language models in various tasks.

context-faithful prompting (1)

A Comparative Study of Prompting Strategies for Legal Text Classification A Framework for Exploring Player Perceptions ofLLM-Generated Dialogue in Commerc... A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module forChinese Spe...

Language Model Robustness 69

Research focuses on ensuring language models can perform reliably under various conditions and resist adversarial perturbations.

factual associationsanalysing classical structuresblackbird language matricesattacks against models

A Black-Box Attack on Code Models via Representation Nearest Neighbor Search A Computational Interface to Translate Strategic Intent from Unstructured Langua... A Framework for Bidirectional Decoding: Case Study in Morphological Inflection

Bias Mitigation in AI 58

This area investigates strategies to identify, measure, and reduce bias in AI systems, aiming for more equitable outcomes.

intersectional fairnessfairness definitionsdebiasing methodspreventing bias

A Causal View of Entity Bias in (Large) Language Models A Novel Contrastive Learning Method for Clickbait Detection onRoCliCo: ARomanian... A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained...

Emotion Recognition & Generation 39

Research in this area focuses on understanding and generating emotional responses in dialogues to enhance human-computer interaction.

emotion annotations (1)dialogue quality (1)

A Challenging Multimodal Video Summary: Simultaneously Extracting and Generating... A General-Purpose Multilingual Document Encoder A Table-to-Text Framework with Heterogeneous Multidominance Attention and Self-E...

Graph Neural Networks 18

This field explores the use of graph-based structures for improved reasoning and inference in various machine learning tasks.

graph-guided reasoningmedical-item graphevent causality inferencedepth of inference

3DRP-Net: 3DRelative Position-aware Network for 3DVisual Grounding A Benchmark for Semi-Inductive Link Prediction in Knowledge Graphs A Fast Method to Filter Noisy Parallel DataWMT2023 Shared Task on Parallel Data ...

ICAIF 2023

ACM International Conference on AI in Finance 79 papers

+

Generative Modeling in Finance 11

Research in this domain centers on the use of generative models to simulate financial data and develop risk management strategies.

GANs (1)

Efficient Event Series Data Modeling via First-Order Constrained Optimization Dyn-GWN: Time-Series Forecasting using Time-varying Graphs with Applications to ... Variational Inference for GARCH-family Models

Reinforcement Learning in Finance 10

Research in this area explores the application of reinforcement learning techniques for optimizing financial decision-making and trading strategies.

deep hedging (2)

Adversarial Deep Hedging: Learning to Hedge without Price Process Modeling Quantifying Outlierness of Funds from their Categories using Supervised Similari... DRL Trading with CPT Actor and Truncated Quantile Critics

Natural Language Processing for Finance 10

This topic investigates the application of NLP techniques to analyze and extract insights from financial texts and reports for improved predictions.

financial analyst reports (1)LLMs (3)textual factors (1)

Predictability of Post-Earnings Announcement Drift with Textual and Contextual F... Modeling Momentum Spillover with Economic Links Discovered from Financial Docume... A supervised generative optimization approach for tabular data

Financial Time-Series Forecasting 9

This topic focuses on methods and models for predicting financial time series data, addressing challenges such as volatility and structural dependencies.

volatility prediction (1)

Multi-Modal Financial Time-Series Retrieval Through Latent Space Projections Lifting Volterra Diffusions via Kernel Decomposition Large Scale Financial Time Series Forecasting with Multi-faceted Model

Optimization Methods for Financial Models 8

Research focuses on optimization techniques to enhance the performance and reliability of financial models and simulations.

gradient-assisted calibration (1)

Turbo-Charging Deep Learning Methods for Partial Differential Equations Dynamic Covariance Estimation under Structural Assumptions via a Joint Optimizat... Gradient-Assisted Calibration for Financial Agent-Based Models

Statistical Arbitrage Techniques 8

This topic encompasses methods for identifying and exploiting pricing inefficiencies in financial markets through statistical methods.

portfolio optimization (1)financial networks (1)

FinBERT-FOMC: Fine-Tuned FinBERT Model with Sentiment Focus Method for Enhancing... Portfolio Optimization via Credal Probabilistic Circuits Mbt-gym: Reinforcement learning for model-based limit order book trading

Anomaly Detection in Finance 7

This topic encompasses methodologies for detecting anomalies in financial data and events to improve risk management and decision-making.

human-in-the-loop (1)

Conditional Generators for Limit Order Book Environments: Explainability, Challe... From Detection to Action: a Human-in-the-loop Toolkit for Anomaly Reasoning and ... Cryptocurrency volatility forecasting using commonality in intraday volatility

Graph Neural Networks for Finance 6

Research focuses on leveraging graph neural network architectures to model complex relationships and dynamics within financial networks and transactions.

dynamic graphs (1)

The Default Cascade Process in Stochastic Financial Networks From random-walks to graph-sprints: a low-latency node embedding framework on co... Reinforcement Learning for Combining Search Methods in the Calibration of Econom...

Event-Driven Market Analysis 3

This area focuses on understanding market reactions to significant events and their impact on financial metrics through advanced analytical techniques.

post-earnings driftevent series datacontextual factorseconomic links

CVA Hedging with Reinforcement Learning Robust Market Making: To Quote, or not To Quote E2EAI: End-to-End Deep Learning Framework for Active Investing

Explainable AI in Finance 2

This area explores techniques for enhancing the interpretability and transparency of AI models applied to financial decision-making.

dual neural networks (1)

Modeling Inverse Demand Function with Explainable Dual Neural Networks Bayesian Networks Improve Out-of-Distribution Calibration for Agribusiness Delin...

ICCV 2023

International Conference on Computer Vision 2,156 papers

+

Object Detection & Tracking 253

Techniques and methodologies for detecting and tracking objects in images or videos, including both 2D and 3D contexts.

visual object tracking (2)3D object detection (9)

Sub-topics:

3D Object Detection Techniques (64)

Self-Supervised Learning for Object Detection (46)

Instance Segmentation Approaches (36)

Domain Adaptation for Object Detection (36)

Vision and Language Integration (23)

Benchmarking Object Detection Models (22)

360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Tracking 3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets 3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object...

Generative Models & View Synthesis 166

Focuses on the development of generative models that can create new image views based on existing data, particularly in 3D environments.

novel view synthesis (2)image generation (10)neural radiance fields (6)

Sub-topics:

3D Object Detection Techniques (45)

Adversarial Training in Generative Models (37)

View Synthesis Algorithms (31)

Diffusion for Image Synthesis (20)

Point Cloud Generation Techniques (19)

3D Human Pose Estimation (14)

3D Motion Magnification: Visualizing Subtle Motions from Time-Varying Radiance F... 3D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editin... 3D VR Sketch Guided 3D Shape Prototyping and Exploration

3D Human Pose Estimation 87

Methods focused on accurately estimating human poses in three-dimensional space, often leveraging video data and accounting for occlusions.

3D human modelingocclusion handlingjoint estimationvideo analysis

2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Super... 3D Distillation: Improving Self-Supervised Monocular Depth Estimation on Reflect... 3D Human Mesh Recovery with Sequentially Global Rotation Estimation

Meta-Learning Techniques 86

Exploration of methods that enhance learning efficiency and adaptability through techniques that leverage previous learning experiences.

forward transferbackward transferadaptive ensembleslearning from few samples

A Game of Bundle Adjustment - Learning Efficient Convergence A Generalist Framework for Panoptic Segmentation of Images and Videos A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learni...

Adversarial Learning & Robustness 71

Research dedicated to improving the robustness of models against adversarial attacks and enhancing their performance under various adversarial conditions.

transferability (2)

3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping ARNOLD: A Benchmark for Language-Grounded Task Learning with Continuous States i... Adaptive Positional Encoding for Bundle-Adjusting Neural Radiance Fields

Quantization & Model Efficiency 68

Techniques aimed at reducing the complexity of models while maintaining performance, particularly through quantization and efficient architectures.

quantization-aware trainingenergy-based modelselastic quantizationmodel compression

A 5-Point Minimal Solver for Event Camera Relative Motion Estimation A Multidimensional Analysis of Social Biases in Vision Transformers A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance

Diffusion Model Architectures 66

Research focused on the design and improvement of diffusion models for various applications, including image synthesis and conditional generation tasks.

image generation (2)

3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cl... A Complete Recipe for Diffusion Generative Models A Dynamic Dual-Processing Object Detection Framework Inspired by the Brain's Rec...

Light and Video Enhancement Techniques 66

Focuses on improving visual quality and interpretability of images and videos under challenging lighting conditions.

low-light video enhancement (2)illumination disentanglement (1)semantic segmentation (3)

A Benchmark for Chinese-English Scene Text Image Super-Resolution Accurate and Fast Compressed Video Captioning Adverse Weather Removal with Codebook Priors

Graph and Spatial Reasoning 49

Research focused on representing and utilizing spatial relationships and graphical structures in understanding and processing data.

spatial knowledge distillation (1)

2D3D-MATR: 2D-3D Matching Transformer for Detection-Free Registration Between Im... 4D Myocardium Reconstruction with Decoupled Motion and Shape Model Anchor-Intermediate Detector: Decoupling and Coupling Bounding Boxes for Accurat...

In-Context Learning & NLP 41

Techniques that leverage context to enhance learning and performance in NLP tasks, particularly through in-context demonstrations.

document information extraction (1)

A Large-Scale Outdoor Multi-Modal Dataset and Benchmark for Novel View Synthesis... A Simple Recipe to Meta-Learn Forward and Backward Transfer A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection

ICML 2023

International Conference on Machine Learning 1,828 papers

+

Efficient Algorithms for ML 389

This topic investigates techniques aimed at improving the efficiency and effectiveness of machine learning algorithms and model inference.

compute-lite (1)distillation (7)inference (5)

Sub-topics:

Dynamic Optimization Strategies (110)

Robust Learning Techniques (63)

Graph Neural Network Efficiency (48)

Privacy in Learning Algorithms (41)

Distributed Optimization Techniques (38)

Advanced Variational Inference Methods (37)

Convergence of First-Order Methods for Constrained Nonconvex Optimization with D... Recasting Self-Attention with Holographic Reduced Representations The Saddle-Point Method in Differential Privacy

Probabilistic Inference and Learning 269

This topic revolves around methods for making probabilistic inferences and learning patterns within uncertain models.

variational inferencestructural biasesnonlinear Markov chainsself-normalization

Sub-topics:

Statistical Learning Theory (51)

Online Learning Strategies (50)

Generative Modeling Approaches (49)

Causal Inference Methods (34)

Uncertainty Quantification (25)

Exploration Techniques in Reinforcement Learning (23)

Data Structures for Density Estimation A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Te... On the Privacy-Robustness-Utility Trilemma in Distributed Learning

Reinforcement Learning Frameworks 202

This topic covers advancements in reinforcement learning techniques and frameworks designed to optimize decision-making in dynamic and complex environments.

policy gradient (6)actor-critic (3)multi-goal (1)exploration (9)

Sub-topics:

Exploration Strategies in RL (86)

Model-Based Reinforcement Learning (30)

Transfer Learning in RL (25)

Multi-Agent Reinforcement Learning (20)

Off-Policy Learning Algorithms (19)

Temporal Difference Learning (9)

Atari-5: Distilling the Arcade Learning Environment down to Five Games Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes Reinforcement Learning with General Utilities: Simpler Variance Reduction and La...

Causal Inference in ML 177

Research in this area focuses on methodologies for understanding and estimating causal relationships within machine learning models.

causal effects (4)multi-task learning (2)belief representations (1)

Sub-topics:

Causal Representation Learning (120)

Causal Discovery Algorithms (32)

Counterfactual Inference Techniques (9)

Confounding Variable Adjustment (8)

Interventional Data Analysis (8)

Generalization on the Unseen, Logic Reasoning and Degree Curriculum Comparison of meta-learners for estimating multi-valued treatment heterogeneous ... Constrained Causal Bayesian Optimization

Image and Speech Processing 169

This area addresses advancements in processing and generating visual and auditory information using machine learning techniques.

weak supervision (1)

Sub-topics:

Robustness in Image Classification (91)

Latent Variable Models for Images (29)

Text-to-Image Generation (7)

Generative Models for Speech (4)

Action Recognition in Videos (4)

Temporal Data Processing in Speech (3)

SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification Towards credible visual model interpretation with path attribution Exponential Smoothing for Off-Policy Learning

Graph Neural Networks 160

This research area explores novel approaches and enhancements in graph neural networks for processing and understanding graph-structured data.

multigrid (1)

Sub-topics:

Graph-based Learning Applications (49)

Robustness in Graph Neural Networks (39)

Learning Dynamics on Graphs (37)

Graph Neural Network Architectures (32)

Attention Mechanisms in GNNs (3)

ClusterFuG: Clustering Fully connected Graphs by Multicut Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning Half-Hop: A graph upsampling approach for slowing down message passing

Stochastic Dynamics and Games 106

Research in this category investigates the learning and optimization of strategies in stochastic environments and games.

mean-field (1)

Sub-topics:

Adaptive Algorithms for Stochastic Processes (42)

Causal Inference in Dynamic Systems (23)

Reinforcement Learning with Stochastic Dynamics (18)

Differentially Private Stochastic Optimization (14)

Online Learning in Stochastic Games (9)

Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making SAM operates far from home: eigenvalue regularization as a dynamical phenomenon Second-order regression models exhibit progressive sharpening to the edge of sta...

Adversarial Robustness in Learning 96

Research here focuses on developing strategies to enhance the robustness of machine learning models against adversarial attacks.

adversarial training (2)

BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Program... Paging with Succinct Predictions Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution...

Diffusion Model Architectures 81

This topic involves the development and application of diffusion models for generating data across various modalities.

energy-based modelsmasked transformerscompositional generationreflected diffusion

Toward Large Kernel Models Adaptive IMLE for Few-shot Pretraining-free Generative Modelling Scaling Laws for Generative Mixed-Modal Language Models

Hyperparameter Optimization 59

Focused on techniques for tuning hyperparameters in machine learning models to improve performance and efficiency.

conformal quantile regressionadaptive explorationvariational inferencetest-time adaptation

Hypothesis Transfer Learning with Surrogate Classification Losses: Generalizatio... Near-Optimal Φ-Regret Learning in Extensive-Form Games Neural Algorithmic Reasoning with Causal Regularisation

NeurIPS 2023

Neural Information Processing Systems 3,540 papers

+

Dynamic Model Training Techniques 330

Advancement of algorithmic strategies for optimizing the training processes of machine learning models under various constraints.

Gradient Descent (3)

Sub-topics:

Data-Efficient Learning Techniques (95)

Dynamic Contextual Adaptation (94)

Active Learning Strategies (47)

Asynchronous Model Training (30)

Adaptive Learning Rate Techniques (24)

Mitigating Catastrophic Forgetting (19)

S³: Increasing GPU Utilization during Generative Inference for Higher Throughput... p-Poisson surface reconstruction in curl-free flow from point clouds (Amplified) Banded Matrix Factorization: A unified approach to private training

Reinforcement Learning Innovations 123

Investigation of novel approaches to enhance decision-making processes in reinforcement learning environments.

Function Approximation (1)

Sub-topics:

Skill Discovery in RL (22)

Reinforcement Learning for Visual Tasks (22)

Hierarchical Reinforcement Learning (16)

Multi-Objective Reinforcement Learning (5)

TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Le... A Comprehensive Benchmark for Neural Human Radiance Fields A Long N-step Surrogate Stage Reward for Deep Reinforcement Learning

Data-Centric AI Evaluation 114

Methods to improve and evaluate the quality and effectiveness of datasets used in machine learning models.

Imitation Learning (1)

Sub-topics:

Benchmarking for Model Evaluation (52)

Robustness in Data Shifts (34)

Causal Inference in Evaluation (9)

Data Valuation Techniques (7)

Transfer Learning in Evaluation (7)

Bias Mitigation in SGD (5)

L₂-Uniform Stability of Randomized Learning Algorithms: Sharper Generalization B... EFWI: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of G... M⁴: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution M...

Causal Inference Models 110

Applying causal discovery techniques to infer relationships and improve interpretability in machine learning models.

Active Causal Discovery (1)Causal Interpretation (1)Multi-Fidelity Experiments (1)Knowledge Graphs (1)

Sub-topics:

Causal Inference Algorithms (47)

Causal Discovery Techniques (36)

Causal Effect Estimation (24)

H-Consistency Bounds: Characterization and Extensions -fractional core stability in Hedonic Games. (Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrep...

Self-Supervised Learning Strategies 86

Exploration of alternative approaches and challenges in self-supervised learning, focusing on model generalization and bias mitigation.

Weak Supervision (1)

A Bounded Ability Estimation for Computerized Adaptive Testing A Definition of Continual Reinforcement Learning A Privacy-Friendly Approach to Data Valuation

Multimodal Learning Approaches 59

Techniques aimed at improving learning from multiple modalities for enhanced model performance in related tasks.

Cross Modal GeneralizationIntegrated PerceptionAudio-Visual LocalizationPoint Cloud Understanding

3D Indoor Instance Segmentation in an Open-World 3D molecule generation by denoising voxel grids 3D-Aware Visual Question Answering about Parts, Poses and Occlusions

Graph Neural Networks for Dynamics 55

Application of graph neural networks to analyze and model dynamic, structured data in various domains.

Dynamical Systems (1)Link Prediction (1)

A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incr... A General Framework for Equivariant Neural Networks on Reductive Lie Groups A General Framework for Robust G-Invariance in G-Equivariant Networks

Adversarial Robustness Techniques 53

Research focusing on enhancing model performance and resilience against adversarial attacks and noisy inputs.

Certified RobustnessStable LearningNoise MitigationModel Perturbation

A Bayesian Take on Gaussian Process Networks A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints A Theory of Transfer-Based Black-Box Attacks: Explanation and Implications

Transformer Architectures for NLP 26

Utilization and modification of transformer models for improved natural language understanding and generation tasks.

Directed Acyclic TransformersSelf-Attention MechanismContextual EmbeddingsPrompt Tuning

SE(3) Equivariant Convolution and Transformer in Ray Space A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Spac... A Logic for Expressing Log-Precision Transformers

Federated Learning Frameworks 9

Research on techniques improving the efficiency and robustness of decentralized machine learning models while ensuring privacy.

Vertical Federated Learning (1)Communication Efficiency (1)

A²CiD²: Accelerating Asynchronous Communication in Decentralized Deep Learning... A Unified Solution for Privacy and Communication Efficiency in Vertical Federate... Adaptive Test-Time Personalization for Federated Learning

ICAIF 2022

ACM International Conference on AI in Finance 60 papers

+

Reinforcement Learning for Finance 10

Research focused on applying reinforcement learning techniques to optimize trading strategies, pricing models, and risk management in financial markets.

dynamic pricingorder routingmodel calibrationportfolio management

Cost-Efficient Reinforcement Learning for Optimal Trade Execution on Dynamic Mar... Market Making under Order Stacking Framework: A Deep Reinforcement Learning Appr... Learning to simulate realistic limit order book markets from data as a World Age...

Graph-Based Financial Modeling 10

Utilizing graph structures and neural networks to enhance predictions and understanding of financial systems and relationships.

graph neural networks (1)

Multivariate Realized Volatility Forecasting with Graph Neural Network Risk-Aware Linear Bandits with Application in Smart Order Routing Offline Deep Reinforcement Learning for Dynamic Pricing of Consumer Credit

Time Series Analysis in Finance 9

Focusing on methodologies for analyzing and forecasting financial time series data, accounting for stability and temporal dynamics.

asset ranking (1)

Sequential asset ranking in nonstationary time series Can maker-taker fees prevent algorithmic cooperation in market making? Computationally Efficient Feature Significance and Importance for Predictive Mod...

Fraud Detection Methodologies 8

Developing techniques and models aimed at detecting fraudulent activities in financial contexts, leveraging advanced learning paradigms.

self-supervised learning (1)

Sequential Banking Products Recommendation and User Profiling in One Go Learning Not to Spoof LaundroGraph: Self-Supervised Graph Representation Learning for Anti-Money Laund...

Optimization in Financial Algorithms 7

Methods for optimizing algorithmic performance in financial settings, including parameter tuning and robust design strategies.

mean-variance efficiency (1)

Dark-Pool Smart Order Routing: a Combinatorial Multi-armed Bandit Approach Optimal Stopping with Gaussian Processes Online Learning for Mixture of Multivariate Hawkes Processes

Synthetic Data Generation 6

Investigating techniques for generating synthetic data to bolster training and testing of financial models, emphasizing robustness and variety.

data augmentationstyle transferGANsself-supervision

Mapping of Financial Services datasets using Human-in-the-Loop Collusion Resistant Federated Learning with Oblivious Distributed Differential P... Differential Liquidity Provision in Uniswap v3 and Implications for Contract Des...

Model Calibration Techniques 3

Developing and refining methods to accurately calibrate financial models based on observed data, enhancing predictive capabilities.

bayesian methodsoutput seriesparameter estimationdynamic models

Model-Agnostic Pricing of Exotic Derivatives Using Signatures Graph and tensor-train recurrent neural networks for high-dimensional models of ... Core Matrix Regression and Prediction with Regularization

Multi-Agent Systems in Finance 3

Exploring frameworks where multiple agents interact within financial systems, facilitating novel strategies and insights into market behavior.

collaborative learningagent-based modelingmean field controlorder flow dynamics

Efficient Calibration of Multi-Agent Simulation Models from Output Series with B... Strategic Asset Allocation with Illiquid Alternatives Addressing Non-Stationarity in FX Trading with Online Model Selection of Offline...

Credit Scoring Models 2

Investigating machine learning approaches for developing credit scoring models that meet regulatory requirements while ensuring accurate assessments.

monotonic neural networksstatistical learningrisk assessmentpredictive stability

Monotonic Neural Additive Models: Pursuing Regulated Machine Learning Models for... Theoretically Motivated Data Augmentation and Regularization for Portfolio Const...

Market Mechanism Design 2

Research on designing mechanisms and structures in financial markets to enhance efficiency and fairness among participants.

equitable marketplacecontract designincentivesmarket making

StyleTime: Style Transfer for Synthetic Time Series Generation Intelligent Inventory Management for Cryptocurrency Brokers

ICAIF 2021

ACM International Conference on AI in Finance 52 papers

+

Market Simulation Techniques 8

This topic investigates various methods for accurately simulating financial markets, including techniques for discrete events and multiple interacting agents.

discrete event simulation (1)

ABIDES-gym: gym environments for multi-agent discrete event simulation and appli... Towards a fully rl-based market simulator Bit by bit: how to realistically simulate a crypto-exchange

Reinforcement Learning in Finance 8

This topic focuses on the application of reinforcement learning techniques to automate and optimize trading strategies and portfolio management in financial markets.

deep reinforcement learning (2)portfolio management (1)

Explainable deep reinforcement learning for portfolio management: an empirical a... Tradeoffs in streaming binary classification under limited inspection resources Deep risk model: a deep learning solution for mining latent risk factors to impr...

Financial Risk Modeling 7

This topic focuses on leveraging machine learning techniques to improve the modeling and prediction of financial risks associated with various investment portfolios.

deep risk modelslatent risk factorscovariance matrix estimationrisk prediction

A hybrid model for forecasting short-term electricity demand The evolving causal structure of equity risk factors The efficient hedging frontier with deep neural networks

Imbalanced Data Handling 7

Research here emphasizes techniques to effectively manage and learn from imbalanced datasets, particularly within financial contexts like fraud detection and trading.

active learning (1)cold start (1)

Active learning for imbalanced data under cold start AuthSHAP: authentication vulnerability detection on tabular data in black box se... FinRL-podracer: high performance and scalable deep reinforcement learning for qu...

Graph-Based Financial Analysis 5

Research in this arena utilizes graph-based learning techniques to analyze complex relationships and structures within financial datasets, such as funds or corporate mergers.

graph neural networksfund similaritymerger predictionnetwork modeling

Learning knowledge-enriched company embeddings for investment management An automated portfolio trading system with feature preprocessing and recurrent r... An agent-based model of strategic adoption of real-time payments

Adversarial Robustness in Trading Algorithms 4

This topic centers on the challenges and solutions related to enhancing the robustness and security of machine learning algorithms used in trading against adversarial manipulation.

adversarial attacks (1)high-frequency trading (1)

Trading via selective classification Adversarial attacks on machine learning systems for high-frequency trading On the current and emerging challenges of developing fair and ethical AI solutio...

Agent-Based Models in Finance 4

This area explores the use of agent-based models to analyze and simulate the behaviors and strategies of market participants in various financial scenarios.

equilibrium strategiesmarket maker analysisstrategic adoptiongame theory

Profit equitably: an investigation of market maker's impact on equitable ou... Financial network games Graph neural network for merger and acquisition prediction

Natural Language Processing for Finance 4

This topic focuses on employing natural language processing techniques to extract insights from financial texts and documents to predict market trends.

stock price prediction (1)

Pre-training and evaluation of numeracy-oriented language model Time horizon-aware modeling of financial texts for stock price prediction Deep Q-learning market makers in a multi-agent simulated stock market

Generative Models for Market Data 2

Research in this area concentrates on using generative models, such as GANs, to realistically simulate financial market data for better analysis and strategy development.

GANstime series generationsimulated market dataconditional generation

Synthesizing credit card transactions Towards realistic market simulations: a generative adversarial networks approach

Privacy-Preserving Finance Solutions 1

Research in this area focuses on developing methodologies to safeguard individual or institutional financial data while still performing analytics and operations.

privacy preservationsecure transactionsdata securityportfolio privacy

Privacy-preserving portfolio pricing

ICAIF 2020

ACM International Conference on AI in Finance 53 papers

+

Deep Learning for Time Series Forecasting 13

Utilization of deep learning architectures specifically designed for forecasting and analyzing financial time series data.

conditional mutual information (1)financial time series (1)

Optimal, truthful, and private securities lending Mixed membership recurrent neural networks for modeling customer purchases Navigating the dynamics of financial embeddings over time

Automated Trading Systems 12

Investigation of automated systems that leverage machine learning and reinforcement learning investments for stock trading under varying market conditions.

stock trading strategiesensemble methodsdeep reinforcement learningfinancial modeling

A hybrid learning approach to detecting regime switches in financial markets Quantifying ESG alpha using scholar big data: an automated machine learning appr... Unsupervised-learning financial reconciliation: a robust, accurate approach insp...

Portfolio & Risk Management Techniques 6

Focus on the development and assessment of advanced techniques and models for managing risk and optimizing portfolios in capital markets.

risk aversionhedging strategiessecurities lendingbayesian methods

Sig-SDEs model for quantitative finance Dynamic prediction length for time series with sequence to sequence network Social media data reveals signal for public consumer perceptions

Federated Learning for Financial Data 5

Exploration of federated learning techniques that enhance data privacy and collaboration in financial modeling without compromising sensitive information.

secure multi-party computation (1)financial applications (1)

SecretMatch: inventory matching from fully homomorphic encryption Differentially private secure multi-party computation for federated learning in ... CryptoCredit: securely training fair models

Anomaly Detection in Transactions 5

Development of techniques to identify and mitigate anomalies in financial transaction data, leveraging machine learning methods.

subgraph anomaly detectionmoney laundering detectiontransaction networksunsupervised learning

Simulating and classifying behavior in adversarial environments based on action-... SURF: improving classifiers in production by learning from busy and noisy end us... Machine learning methods to detect money laundering in the bitcoin blockchain in...

Transaction Cost Optimization 4

Focus on optimizing trading strategies in relation to transaction costs, including the development of algorithms to minimize financial impact.

portfolio optimizationonline gradient descenttransaction costsscheduling strategies

Towards self-regulating AI: challenges and opportunities of AI model governance ... Understanding distributional ambiguity via non-robust chance constraint A multi-faceted approach to large scale financial forecasting

Reinforcement Learning in Finance 3

Research focusing on the application of reinforcement learning techniques to modeling and optimizing financial decision-making processes.

batch reinforcement learning (1)

Foreign exchange trading: a risk-averse batch reinforcement learning approach Multi-agent reinforcement learning in a realistic limit order book market simula... Improved predictive deep temporal neural networks with trend filtering

Market Sentiment Analysis 3

Research on extracting and analyzing sentiment from diverse data sources such as social media and news to understand market movements.

social media signalsconsumer perceptionsnews topic relevancestock market impact

What can be learned from satisfaction assessments? Predicting the behavior of dealers in over-the-counter corporate bond markets Fast direct calibration of interest rate derivatives pricing models

Synthetic Data Generation in Finance 1

Investigation into methods for generating synthetic financial data to address the constraints of real-world data availability and its implications.

challenges (1)opportunities (1)

Generating synthetic data in finance: opportunities, challenges and pitfalls

Image-Based Financial Analysis 1

Application of computer vision techniques to analyze and extract insights from financial documents and visual information.

image classificationfinancial documentsdeep learningvisual data extraction

An analysis of political turmoil effects on stock prices: a case study of US-Chi...

Conference Papers

Conference Calendar

Paper Analysis by Venue

ACL 2025

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

AFA 2025

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

CVPR 2025

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

EMNLP 2025

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

ICCV 2025

ICML 2025

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

NAACL 2025

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

ACL 2024

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

AFA 2024

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

CVPR 2024

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

EACL 2024

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

EMNLP 2024

📈 Growing Topics

🆕 Emerging Topics

ICAIF 2024

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

ICML 2024

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

NAACL 2024

NeurIPS 2024

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

ACL 2023

AFA 2023

CVPR 2023

EACL 2023

EMNLP 2023

ICAIF 2023

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

ICCV 2023

ICML 2023

NeurIPS 2023

ICAIF 2022

📈 Growing Topics

📉 Declining Topics

🆕 Emerging Topics

ICAIF 2021

📈 Growing Topics

📉 Declining Topics

ICAIF 2020