| tech.blog / monetary.live / ivan.digital
March 13, 2026 at 04:37 UTC
🤗 HuggingFace Daily Papers
Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
▲ 28 🏢 Tencent Hunyuan
  • Spatial-TTT enables streaming visual-based spatial intelligence through test-time training that adapts parameters to capture spatial evidence over lon
DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Iden
▲ 11 🎓 Fudan University
  • DreamVideo-Omni is a unified framework for video synthesis that enables precise multi-subject identity control and multi-granularity motion manipulati
IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
▲ 11 🎓 Tsinghua University
  • IndexCache reduces sparse attention computation in large language models by reusing top-k token selections across layers, achieving significant speedu
ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA
▲ 11 🎓 Tel Aviv University
  • ID-LoRA enables joint generation of visual appearance and voice using a single model, improving personalization through identity-driven in-context LoR
ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation
▲ 10 🎓 The Hong Kong University of Science and Technology
  • ShotVerse enables cinematic video generation through a plan-then-control framework that decouples textual planning from camera control using vision-la
Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Ed
▲ 7 🎓 SJTU VisionXLab
  • Reinforcement learning framework with novel reward modeling and benchmarking approaches improves fidelity and instruction adherence in image editing a
Test-Time Training 1Fast Weights 1Spatial Evidence 1Long-Horizon Scene Videos 1Hybrid Architecture 1Sliding-Window Attention 13D Spatiotemporal Convolution 1Spatial-Predictive Mechanism 1Video Spatial Benchmarks 1Diffusion Models 2Image Editing 2Classifier-Free Guidance 2
🏛️ Top Research Institutions
One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers
🏛️ Rice University AI & Machine Learning
  • Existing generative models struggle with balancing computational resources and quality in image generation.
  • The Elastic Latent Interfaces framework allows diffusion transformers to adaptively allocate computation based on budget
STADA: Specification-based Testing for Autonomous Driving Agents
🏛️ University of Virginia Software & Programming
  • Validating autonomous driving agents before real-world deployment is complex and requires diverse testing scenarios.
  • A specification-based testing framework for autonomous driving agents that ensures comprehensive validation through simu
Tetris is Hard with Just One Piece Type
🏛️ MIT Theory & Algorithms
  • The computational complexity of Tetris, a widely recognized game, remains poorly understood.
  • Analyzing the complexity of Tetris clearing and survival with a focus on a single piece type.
Double Machine Learning for Time Series
🏛️ Sapienza University of Rome Economics
  • Traditional Double Machine Learning methods are limited in their applicability to macroeconomic time-series data.
  • A modified Double Machine Learning estimator that incorporates a deterministic cross-fitting step, termed Reverse Cross-
AI & Machine Learning
461 papers 7 cats
Systems & Infrastructure
34 papers 6 cats
Software & Programming
13 papers 4 cats
Theory & Algorithms
24 papers 5 cats
Applications
106 papers 7 cats
Other CS
29 papers 8 cats
Quantitative Finance
16 papers 9 cats
Economics
9 papers 3 cats