Daily Papers of 2026-03-17

  1. AI Can Learn Scientific Taste 397 upvotes, #1 of 2026-03-17
  2. Attention Residuals 155 upvotes, #2 of 2026-03-17
  3. HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions 149 upvotes, #3 of 2026-03-17
  4. Grounding World Simulation Models in a Real-World Metropolis 145 upvotes, #4 of 2026-03-17
  5. EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings 142 upvotes, #5 of 2026-03-17
  6. OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data 142 upvotes, #5 of 2026-03-17
  7. Mixture-of-Depths Attention 77 upvotes, #7 of 2026-03-17
  8. Effective Distillation to Hybrid xLSTM Architectures 32 upvotes, #8 of 2026-03-17
  9. Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models 28 upvotes, #9 of 2026-03-17
  10. Safe and Scalable Web Agent Learning via Recreated Websites 25 upvotes, #10 of 2026-03-17
  11. ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer 24 upvotes, #11 of 2026-03-17
  12. POLCA: Stochastic Generative Optimization with LLM 22 upvotes, #12 of 2026-03-17
  13. EvoClaw: Evaluating AI Agents on Continuous Software Evolution 20 upvotes, #13 of 2026-03-17
  14. WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics 19 upvotes, #14 of 2026-03-17
  15. TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning 18 upvotes, #15 of 2026-03-17
  16. Motivation in Large Language Models 16 upvotes, #16 of 2026-03-17
  17. Make it SING: Analyzing Semantic Invariants in Classifiers 16 upvotes, #16 of 2026-03-17
  18. MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos 13 upvotes, #18 of 2026-03-17
  19. Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty 11 upvotes, #19 of 2026-03-17
  20. Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models 10 upvotes, #20 of 2026-03-17
  21. Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching 10 upvotes, #20 of 2026-03-17
  22. The PokeAgent Challenge: Competitive and Long-Context Learning at Scale 10 upvotes, #20 of 2026-03-17
  23. Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning 10 upvotes, #20 of 2026-03-17
  24. FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach 9 upvotes, #24 of 2026-03-17
  25. Panoramic Affordance Prediction 9 upvotes, #24 of 2026-03-17
  26. RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense Forecasting 8 upvotes, #26 of 2026-03-17
  27. Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods 8 upvotes, #26 of 2026-03-17
  28. Learning Latent Proxies for Controllable Single-Image Relighting 8 upvotes, #26 of 2026-03-17
  29. Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange 6 upvotes, #29 of 2026-03-17
  30. VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting 6 upvotes, #29 of 2026-03-17
  31. HorizonMath: Measuring AI Progress Toward Mathematical Discovery with Automatic Verification 6 upvotes, #29 of 2026-03-17
  32. FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance 5 upvotes, #32 of 2026-03-17
  33. When Does Sparsity Mitigate the Curse of Depth in LLMs 5 upvotes, #32 of 2026-03-17
  34. Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion 5 upvotes, #32 of 2026-03-17
  35. GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering 5 upvotes, #32 of 2026-03-17
  36. OxyGen: Unified KV Cache Management for Vision-Language-Action Models under Multi-Task Parallelism 4 upvotes, #36 of 2026-03-17
  37. Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion 4 upvotes, #36 of 2026-03-17
  38. MoKus: Leveraging Cross-Modal Knowledge Transfer for Knowledge-Aware Concept Customization 3 upvotes, #38 of 2026-03-17
  39. Mind the Shift: Decoding Monetary Policy Stance from FOMC Statements with Large Language Models 3 upvotes, #38 of 2026-03-17
  40. Efficient Document Parsing via Parallel Token Prediction 3 upvotes, #38 of 2026-03-17
  41. Towards Generalizable Robotic Manipulation in Dynamic Environments 3 upvotes, #38 of 2026-03-17
  42. SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis 2 upvotes, #42 of 2026-03-17
  43. Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories 2 upvotes, #42 of 2026-03-17
  44. VoXtream2: Full-stream TTS with dynamic speaking rate control 1 upvotes, #44 of 2026-03-17
  45. sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Notebook 0 upvotes, #45 of 2026-03-17
  46. SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation 0 upvotes, #45 of 2026-03-17

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.