Daily Papers of 2026-11-17

  1. InclusionMed: Benchmarking AI for Inclusive Healthcare 99 upvotes, #1 of 2026-11-17
  2. Sage S2.1 Flash Technical Report 95 upvotes, #2 of 2026-11-17
  3. K2-Horizon: A Frontier Fleet of Open Source Language Models 84 upvotes, #3 of 2026-11-17
  4. AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data 72 upvotes, #4 of 2026-11-17
  5. SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations 51 upvotes, #5 of 2026-11-17
  6. SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection 43 upvotes, #6 of 2026-11-17
  7. ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters 36 upvotes, #7 of 2026-11-17
  8. PaperCritic: Training AI Reviewers to Assess the Soundness of Papers 33 upvotes, #8 of 2026-11-17
  9. LynnReal-Hand: Unlocking World Interaction with Hand Control 22 upvotes, #9 of 2026-11-17
  10. Accelerate Bench: Evaluating Agents for Application-Level Program Optimization 19 upvotes, #10 of 2026-11-17
  11. VoxMel TTS Technical Report 17 upvotes, #11 of 2026-11-17
  12. SALA: Semantically Aligned Latent Actions Enable Dual-Axis Scaling of Embodied Foundation Models 15 upvotes, #12 of 2026-11-17
  13. MovieRoll: A Systematic Framework for Rolling Out Long-Form Videos 15 upvotes, #12 of 2026-11-17
  14. Calpha: Toward Native Biomolecular Intelligence in a General-Purpose Language Model 14 upvotes, #14 of 2026-11-17
  15. Energy-Based Reasoners: Your Recurrent Reasoner Should Be an Energy-Based Model 9 upvotes, #15 of 2026-11-17
  16. Termination Lag: Coding Agents Solve Early but Stop Late 7 upvotes, #16 of 2026-11-17
  17. Correcting Persistent Failures in Point-Cloud Grasping Policies using Human Demonstrations in Virtual Reality 7 upvotes, #16 of 2026-11-17
  18. OutfitterBench: Evaluating LLM Agents on Long-Horizon Resource Allocation and Commitment Coordination 6 upvotes, #18 of 2026-11-17
  19. Marimba: A System One Model for Speech 6 upvotes, #18 of 2026-11-17
  20. DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images 6 upvotes, #18 of 2026-11-17
  21. Latent Feedback Is a Compute and Data Amplifier 6 upvotes, #18 of 2026-11-17
  22. Correct Labels Are Not Enough: Reliable Metadata Can Silently Control Model Behavior 5 upvotes, #22 of 2026-11-17
  23. Ego Guidance: Enhancing Robot Policy Learning with Action-Free Human Egocentric Videos 5 upvotes, #22 of 2026-11-17
  24. More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs 5 upvotes, #22 of 2026-11-17
  25. Continuation-Guided LLM Evolution of Program Policies and Goal Compilers in Craftax 5 upvotes, #22 of 2026-11-17
  26. JEPA4R: Embodied JEPA World Models with 4D Point Planning 5 upvotes, #22 of 2026-11-17
  27. Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment 5 upvotes, #22 of 2026-11-17
  28. BitDecoding-FP4: Native FP4 KV Cache Decoding via Algorithm-System Co-Design 4 upvotes, #28 of 2026-11-17
  29. UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models 4 upvotes, #28 of 2026-11-17
  30. LoopFill: Pipelined Multi-Token Speculative Decoding for Looped Transformers 4 upvotes, #28 of 2026-11-17
  31. Invariant-Aware Harness Enforcement to Protect LLM Agents from Silent API Failures 4 upvotes, #28 of 2026-11-17
  32. Inside the Trading Loop: Markets, Models, and Moves with LLM Agents 3 upvotes, #32 of 2026-11-17
  33. Dataset Distillation via Drifting 3 upvotes, #32 of 2026-11-17
  34. When Expert Disagreement Hurts: Prestige and Selectivity in LLM Decision Revision 3 upvotes, #32 of 2026-11-17
  35. Centered Ablation: Why Last-Layer Directional Ablation Under-Fires or Collapses, and a Closed-Form Fix 3 upvotes, #32 of 2026-11-17
  36. ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization 3 upvotes, #32 of 2026-11-17
  37. GlyphAtlas: Disentangling Stroke Detail from Layout for Scene Text Synthesis 2 upvotes, #37 of 2026-11-17
  38. Flexible Multi-Stack Super-Resolution of Clinical Brain MRI Using Hetero-Orientation Variational Encoding: Expert Reader Evaluation in a Nigerian Cohort 2 upvotes, #37 of 2026-11-17
  39. Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning 1 upvotes, #39 of 2026-11-17
  40. Zuse: A Decision Model for European Languages 1 upvotes, #39 of 2026-11-17
  41. GPBam: A Retrieval-Aware German Public Law Exam Benchmark 1 upvotes, #39 of 2026-11-17
  42. A Reinforcement Learning Method to Navigate SMEFT Operator Space 1 upvotes, #39 of 2026-11-17

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.