Daily Papers of 2026-02-04

  1. CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding 91 upvotes, #1 of 2026-02-04
  2. AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration 84 upvotes, #2 of 2026-02-04
  3. No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs 68 upvotes, #3 of 2026-02-04
  4. MARS: Modular Agent with Reflective Search for Automated AI Research 61 upvotes, #4 of 2026-02-04
  5. 3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation 55 upvotes, #5 of 2026-02-04
  6. daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently 50 upvotes, #6 of 2026-02-04
  7. Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks 46 upvotes, #7 of 2026-02-04
  8. Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis 41 upvotes, #8 of 2026-02-04
  9. SWE-World: Building Software Engineering Agents in Docker-Free Environments 39 upvotes, #9 of 2026-02-04
  10. SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training 36 upvotes, #10 of 2026-02-04
  11. CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs 33 upvotes, #11 of 2026-02-04
  12. Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation 25 upvotes, #12 of 2026-02-04
  13. Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing 24 upvotes, #13 of 2026-02-04
  14. Unified Personalized Reward Model for Vision Generation 19 upvotes, #14 of 2026-02-04
  15. RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval 18 upvotes, #15 of 2026-02-04
  16. WideSeek: Advancing Wide Research via Multi-Agent Scaling 15 upvotes, #16 of 2026-02-04
  17. Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning 15 upvotes, #16 of 2026-02-04
  18. Balancing Understanding and Generation in Discrete Diffusion Models 14 upvotes, #18 of 2026-02-04
  19. Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification 12 upvotes, #19 of 2026-02-04
  20. Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection 12 upvotes, #19 of 2026-02-04
  21. LIVE: Long-horizon Interactive Video World Modeling 12 upvotes, #19 of 2026-02-04
  22. AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning Process 10 upvotes, #22 of 2026-02-04
  23. Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training 9 upvotes, #23 of 2026-02-04
  24. Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch 9 upvotes, #23 of 2026-02-04
  25. FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation 9 upvotes, #23 of 2026-02-04
  26. LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents 8 upvotes, #26 of 2026-02-04
  27. No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding 8 upvotes, #26 of 2026-02-04
  28. LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding 8 upvotes, #26 of 2026-02-04
  29. Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration 7 upvotes, #29 of 2026-02-04
  30. Instruction Anchors: Dissecting the Causal Dynamics of Modality Arbitration 7 upvotes, #29 of 2026-02-04
  31. Position: Agentic Evolution is the Path to Evolving LLMs 5 upvotes, #31 of 2026-02-04
  32. ObjEmbed: Towards Universal Multimodal Object Embeddings 5 upvotes, #31 of 2026-02-04
  33. WorldVQA: Measuring Atomic World Knowledge in Multimodal Large Language Models 5 upvotes, #31 of 2026-02-04
  34. Scaling Small Agents Through Strategy Auctions 5 upvotes, #31 of 2026-02-04
  35. FIRE-Bench: Evaluating Agents on the Rediscovery of Scientific Insights 5 upvotes, #31 of 2026-02-04
  36. Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation 5 upvotes, #31 of 2026-02-04
  37. Accelerating Scientific Research with Gemini: Case Studies and Common Techniques 5 upvotes, #31 of 2026-02-04
  38. Glance and Focus Reinforcement for Pan-cancer Screening 4 upvotes, #38 of 2026-02-04
  39. SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration 4 upvotes, #38 of 2026-02-04
  40. POP: Prefill-Only Pruning for Efficient Large Model Inference 4 upvotes, #38 of 2026-02-04
  41. MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers 3 upvotes, #41 of 2026-02-04
  42. SimpleGPT: Improving GPT via A Simple Normalization Strategy 3 upvotes, #41 of 2026-02-04
  43. Contextualized Visual Personalization in Vision-Language Models 3 upvotes, #41 of 2026-02-04
  44. FaceLinkGen: Rethinking Identity Leakage in Privacy-Preserving Face Recognition with Identity Extraction 2 upvotes, #44 of 2026-02-04
  45. MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning 2 upvotes, #44 of 2026-02-04
  46. RecGOAT: Graph Optimal Adaptive Transport for LLM-Enhanced Multimodal Recommendation with Dual Semantic Alignment 1 upvotes, #46 of 2026-02-04
  47. Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents 1 upvotes, #46 of 2026-02-04
  48. LangMap: A Hierarchical Benchmark for Open-Vocabulary Goal Navigation 1 upvotes, #46 of 2026-02-04
  49. Didactic to Constructive: Turning Expert Solutions into Learnable Reasoning 1 upvotes, #46 of 2026-02-04
  50. MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training 1 upvotes, #46 of 2026-02-04
  51. The Necessity of a Unified Framework for LLM-Based Agent Evaluation 1 upvotes, #46 of 2026-02-04
  52. You Need an Encoder for Native Position-Independent Caching 0 upvotes, #52 of 2026-02-04
  53. Adaptive Evidence Weighting for Audio-Spatiotemporal Fusion 0 upvotes, #52 of 2026-02-04

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.