Daily Papers of 2026-01-14

  1. MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences 74 upvotes, #1 of 2026-01-14
  2. Motion Attribution for Video Generation 66 upvotes, #2 of 2026-01-14
  3. Solar Open Technical Report 61 upvotes, #3 of 2026-01-14
  4. KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions 55 upvotes, #4 of 2026-01-14
  5. ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking 48 upvotes, #5 of 2026-01-14
  6. User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale 48 upvotes, #5 of 2026-01-14
  7. Ministral 3 44 upvotes, #7 of 2026-01-14
  8. ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands 40 upvotes, #8 of 2026-01-14
  9. MemoBrain: Executive Memory as an Agentic Brain for Reasoning 36 upvotes, #9 of 2026-01-14
  10. 3AM: Segment Anything with Geometric Consistency in Videos 33 upvotes, #10 of 2026-01-14
  11. The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents 23 upvotes, #11 of 2026-01-14
  12. Parallel Context-of-Experts Decoding for Retrieval Augmented Generation 18 upvotes, #12 of 2026-01-14
  13. SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices 15 upvotes, #13 of 2026-01-14
  14. Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization 9 upvotes, #14 of 2026-01-14
  15. ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios 8 upvotes, #15 of 2026-01-14
  16. The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios 7 upvotes, #16 of 2026-01-14
  17. UM-Text: A Unified Multimodal Model for Image Understanding 7 upvotes, #16 of 2026-01-14
  18. End-to-End Video Character Replacement without Structural Guidance 7 upvotes, #16 of 2026-01-14
  19. VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory 7 upvotes, #16 of 2026-01-14
  20. VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding 6 upvotes, #20 of 2026-01-14
  21. EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs 5 upvotes, #21 of 2026-01-14
  22. JudgeRLVR: Judge First, Generate Second for Efficient Reasoning 5 upvotes, #21 of 2026-01-14
  23. Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking 2 upvotes, #23 of 2026-01-14
  24. GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models 1 upvotes, #24 of 2026-01-14

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.