Daily Papers of 2026-07-29

  1. HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone 154 upvotes, #1 of 2026-07-29
  2. CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents 111 upvotes, #2 of 2026-07-29
  3. A New Role for Relevance: Guiding Corpus Interaction in Agentic Search 93 upvotes, #3 of 2026-07-29
  4. ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition 65 upvotes, #4 of 2026-07-29
  5. Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model 35 upvotes, #5 of 2026-07-29
  6. Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory 33 upvotes, #6 of 2026-07-29
  7. Pass the Baton: Trajectory-Relayed On-Policy Distillation 33 upvotes, #6 of 2026-07-29
  8. Visual prompt engineering for video models 22 upvotes, #8 of 2026-07-29
  9. Wonder: Video World Model Done Better 21 upvotes, #9 of 2026-07-29
  10. Shieldstral 20 upvotes, #10 of 2026-07-29
  11. PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models 18 upvotes, #11 of 2026-07-29
  12. MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities 18 upvotes, #11 of 2026-07-29
  13. Parallel Decoding Distillation for Fast Image and Video Generation 16 upvotes, #13 of 2026-07-29
  14. Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking 14 upvotes, #14 of 2026-07-29
  15. Reinforcement Learning for Code Optimization 12 upvotes, #15 of 2026-07-29
  16. OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs 9 upvotes, #16 of 2026-07-29
  17. Towards Robust Reinforcement Learning for Small-Scale Language Model Agents 7 upvotes, #17 of 2026-07-29
  18. Uncovering Latent Reasoning Strategies in Language Models 6 upvotes, #18 of 2026-07-29
  19. Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents 6 upvotes, #18 of 2026-07-29
  20. VisualPatchWorld: Code World Models as Latent Structured Representations for Planning 6 upvotes, #18 of 2026-07-29
  21. Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control 6 upvotes, #18 of 2026-07-29
  22. Projection Pursuit CPCANet for Domain Generalization 5 upvotes, #22 of 2026-07-29
  23. GLI-AL: A Multi-Modal Glioma MRI Label Resource with Unified Anatomy-Lesion Labels 5 upvotes, #22 of 2026-07-29
  24. Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization 5 upvotes, #22 of 2026-07-29
  25. Human-in-the-Loop Signature Bootstrapping for UAV Hyperspectral PFM-1 Mine Detection 5 upvotes, #22 of 2026-07-29
  26. Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion 5 upvotes, #22 of 2026-07-29
  27. How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF 4 upvotes, #27 of 2026-07-29
  28. Edge-Aware Thermal Infrared UAV Swarm Tracking 3 upvotes, #28 of 2026-07-29
  29. OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis 2 upvotes, #29 of 2026-07-29

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.