Daily Papers of 2026-07-28

  1. Kimi K3: Open Frontier Intelligence 458 upvotes, #1 of 2026-07-28
  2. Progress Reward Modeling for Robotic Learning: A Comprehensive Survey 192 upvotes, #2 of 2026-07-28
  3. JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents 124 upvotes, #3 of 2026-07-28
  4. From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search 82 upvotes, #4 of 2026-07-28
  5. Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation 76 upvotes, #5 of 2026-07-28
  6. StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents 62 upvotes, #6 of 2026-07-28
  7. Data Pyramid for Embodied Manipulation 36 upvotes, #7 of 2026-07-28
  8. Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification 35 upvotes, #8 of 2026-07-28
  9. Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On 28 upvotes, #9 of 2026-07-28
  10. OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation 26 upvotes, #10 of 2026-07-28
  11. The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation 26 upvotes, #10 of 2026-07-28
  12. dRAE: Representation Autoencoder with Hyper-Spherical Codes 12 upvotes, #12 of 2026-07-28
  13. Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models 11 upvotes, #13 of 2026-07-28
  14. ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding 11 upvotes, #13 of 2026-07-28
  15. Characterizing Warp Divergence from Pascal to Blackwell 9 upvotes, #15 of 2026-07-28
  16. Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models 8 upvotes, #16 of 2026-07-28
  17. Codifying the Judge: Scalable Evaluation via Program Distillation 8 upvotes, #16 of 2026-07-28
  18. Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling 8 upvotes, #16 of 2026-07-28
  19. A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever 7 upvotes, #19 of 2026-07-28
  20. WorldDiT: A Unified Diffusion Architecture for World and Action Modeling 7 upvotes, #19 of 2026-07-28
  21. DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes 7 upvotes, #19 of 2026-07-28
  22. TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs 6 upvotes, #22 of 2026-07-28
  23. UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models 6 upvotes, #22 of 2026-07-28
  24. FilmBench: A Film-Grade Benchmark for Cinematic Video Generation 6 upvotes, #22 of 2026-07-28
  25. GNM Head: A Generative aNthropometric Model of the human head 5 upvotes, #25 of 2026-07-28
  26. A Vocabulary for Multi-Agent Automated Research Systems 4 upvotes, #26 of 2026-07-28
  27. Bitcoin Price Direction Prediction via Regime-Aware Multi-Modal Fusion of Social Sentiment and Technical Features 4 upvotes, #26 of 2026-07-28
  28. TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward 3 upvotes, #28 of 2026-07-28
  29. IndicTalk: A Large-Scale Persona-Based Multilingual Conversational Corpus for Indic Languages 3 upvotes, #28 of 2026-07-28
  30. Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels 3 upvotes, #28 of 2026-07-28
  31. DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification 1 upvotes, #31 of 2026-07-28

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.