Daily Papers of 2026-01-21

  1. Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization 74 upvotes, #1 of 2026-01-21
  2. Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey 59 upvotes, #2 of 2026-01-21
  3. Toward Efficient Agents: Memory, Tool learning, and Planning 49 upvotes, #3 of 2026-01-21
  4. Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models 46 upvotes, #4 of 2026-01-21
  5. Think3D: Thinking with Space for Spatial Reasoning 45 upvotes, #5 of 2026-01-21
  6. OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer 44 upvotes, #6 of 2026-01-21
  7. FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs 34 upvotes, #7 of 2026-01-21
  8. MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models 26 upvotes, #8 of 2026-01-21
  9. LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR 23 upvotes, #9 of 2026-01-21
  10. FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation 21 upvotes, #10 of 2026-01-21
  11. Agentic-R: Learning to Retrieve for Agentic Search 19 upvotes, #11 of 2026-01-21
  12. LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals 18 upvotes, #12 of 2026-01-21
  13. UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation 17 upvotes, #13 of 2026-01-21
  14. ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents 17 upvotes, #13 of 2026-01-21
  15. Aligning Agentic World Models via Knowledgeable Experience Learning 15 upvotes, #15 of 2026-01-21
  16. DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution 15 upvotes, #15 of 2026-01-21
  17. A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification 12 upvotes, #17 of 2026-01-21
  18. KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning 9 upvotes, #18 of 2026-01-21
  19. Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment 8 upvotes, #19 of 2026-01-21
  20. PRiSM: Benchmarking Phone Realization in Speech Models 6 upvotes, #20 of 2026-01-21
  21. InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning 5 upvotes, #21 of 2026-01-21
  22. Beyond Cosine Similarity: Taming Semantic Drift and Antonym Intrusion in a 15-Million Node Turkish Synonym Graph 4 upvotes, #22 of 2026-01-21
  23. A Hybrid Protocol for Large-Scale Semantic Dataset Generation in Low-Resource Languages: The Turkish Semantic Relations Corpus 4 upvotes, #22 of 2026-01-21
  24. Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD 3 upvotes, #24 of 2026-01-21
  25. SciCoQA: Quality Assurance for Scientific Paper--Code Alignment 3 upvotes, #24 of 2026-01-21
  26. On the Evidentiary Limits of Membership Inference for Copyright Auditing 3 upvotes, #24 of 2026-01-21
  27. Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning 3 upvotes, #24 of 2026-01-21
  28. RemoteVAR: Autoregressive Visual Modeling for Remote Sensing Change Detection 2 upvotes, #28 of 2026-01-21
  29. METIS: Mentoring Engine for Thoughtful Inquiry & Solutions 2 upvotes, #28 of 2026-01-21
  30. Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement 2 upvotes, #28 of 2026-01-21
  31. DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems 2 upvotes, #28 of 2026-01-21
  32. Finally Outshining the Random Baseline: A Simple and Effective Solution for Active Learning in 3D Biomedical Imaging 1 upvotes, #32 of 2026-01-21

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.