| tech.blog / monetary.live / ivan.digital
November 01, 2026 at 18:09 UTC
🤗 HuggingFace Daily Papers
Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs
▲ 101 🎓 KAIST
  • LOWN adaptively skips image processing during diffusion vision-language model decoding when predictions agree, reducing computation while preserving a...
A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
▲ 71 🏢 Xiaomi Research
  • A-RSI improves recursive self-improvement by refreshing training tasks based on declining learning signals and using independently verifiable program-...
Proving and Improving the Platonic Representation Hypothesis with JEPAs
▲ 62 🎓 Brown University
  • Joint-embedding predictive architectures trained on aligned multi-modal observations converge to shared representations with far greater efficiency th...
L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory
▲ 39 🎓 KAIST AI
  • L3G-World uses a compact latent 3D Gaussian memory and alternating autoregressive updates with a video diffusion transformer to generate spatially con...
A Broader Look into MLLM's Retrieval Heads
▲ 28 🎓 Institute of Information Engineering, Chinese Academy of Sciences
  • Retrieval heads remain sparse and shared across audio-visual modalities, and optimizing them improves document retrieval performance in multimodal mod...
HairDeck: Animation-Ready Stylized Hair Cards from a Single Image
▲ 23 🎓 Tsinghua University
  • HairDeck generates stylized hair cards and spring-bone animations as unordered token sets using a diffusion transformer, improving accuracy and speed ...
Your Benchmark Is an Empirical Measure Over Difficulty
▲ 21 🎓 University of Illinois Urbana-Champaign
  • This work formalizes benchmark evaluation through difficulty measures, identifies failure modes of measure mismatch and coverage gaps, and proposes di...
Diffusion Vision-Language Models 1Visual Token Pruning 1Llada-V 1Lown 1Masked Tokens 1Key-Value Caching 1Decoding Flops 1Next-Token Prediction 2Recursive Self-Improvement 1Training Dynamics 1Reward Variation 1Task Pool 1
AI & Machine Learning
622 papers 7 cats
Systems & Infrastructure
54 papers 6 cats
Software & Programming
50 papers 4 cats
Theory & Algorithms
81 papers 5 cats
Applications
189 papers 7 cats
Other CS
46 papers 9 cats
Quantitative Finance
12 papers 9 cats
Economics
16 papers 3 cats