Daily Papers of 2026-05-15

  1. Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling 154 upvotes, #1 of 2026-05-15
  2. Self-Distilled Agentic Reinforcement Learning 107 upvotes, #2 of 2026-05-15
  3. Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation 91 upvotes, #3 of 2026-05-15
  4. SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer 80 upvotes, #4 of 2026-05-15
  5. MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models 73 upvotes, #5 of 2026-05-15
  6. MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory 60 upvotes, #6 of 2026-05-15
  7. Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning 59 upvotes, #7 of 2026-05-15
  8. Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems 47 upvotes, #8 of 2026-05-15
  9. WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation 45 upvotes, #9 of 2026-05-15
  10. STALE: Can LLM Agents Know When Their Memories Are No Longer Valid? 44 upvotes, #10 of 2026-05-15
  11. Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video 39 upvotes, #11 of 2026-05-15
  12. RouteProfile: Elucidating the Design Space of LLM Profiles for Routing 30 upvotes, #12 of 2026-05-15
  13. PREPING: Building Agent Memory without Tasks 28 upvotes, #13 of 2026-05-15
  14. Long Context Pre-Training with Lighthouse Attention 27 upvotes, #14 of 2026-05-15
  15. VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction 26 upvotes, #15 of 2026-05-15
  16. Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning 25 upvotes, #16 of 2026-05-15
  17. EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents 24 upvotes, #17 of 2026-05-15
  18. PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World 21 upvotes, #18 of 2026-05-15
  19. FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale 20 upvotes, #19 of 2026-05-15
  20. Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding 19 upvotes, #20 of 2026-05-15
  21. Orchard: An Open-Source Agentic Modeling Framework 19 upvotes, #20 of 2026-05-15
  22. DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models 19 upvotes, #20 of 2026-05-15
  23. ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both 19 upvotes, #20 of 2026-05-15
  24. IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation 16 upvotes, #24 of 2026-05-15
  25. ViMU: Benchmarking Video Metaphorical Understanding 13 upvotes, #25 of 2026-05-15
  26. RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO 13 upvotes, #25 of 2026-05-15
  27. Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models 10 upvotes, #27 of 2026-05-15
  28. WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild 9 upvotes, #28 of 2026-05-15
  29. PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation 9 upvotes, #28 of 2026-05-15
  30. PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution 8 upvotes, #30 of 2026-05-15
  31. CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves 8 upvotes, #30 of 2026-05-15
  32. BOOKMARKS: Efficient Active Storyline Memory for Role-playing 8 upvotes, #30 of 2026-05-15
  33. Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis 8 upvotes, #30 of 2026-05-15
  34. Does Synthetic Layered Design Data Benefit Layered Design Decomposition? 8 upvotes, #30 of 2026-05-15
  35. Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning 7 upvotes, #35 of 2026-05-15
  36. FutureSim: Replaying World Events to Evaluate Adaptive Agents 7 upvotes, #35 of 2026-05-15
  37. Aligning Latent Geometry for Spherical Flow Matching in Image Generation 7 upvotes, #35 of 2026-05-15
  38. Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation 5 upvotes, #38 of 2026-05-15
  39. Topology-Preserving Neural Operator Learning via Hodge Decomposition 5 upvotes, #38 of 2026-05-15
  40. Ideology Prediction of German Political Texts 5 upvotes, #38 of 2026-05-15
  41. LLM-based Detection of Manipulative Political Narratives 5 upvotes, #38 of 2026-05-15
  42. Nexus : An Agentic Framework for Time Series Forecasting 5 upvotes, #38 of 2026-05-15
  43. BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE 5 upvotes, #38 of 2026-05-15
  44. Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image 5 upvotes, #38 of 2026-05-15
  45. Dynamic Latent Routing 4 upvotes, #45 of 2026-05-15
  46. Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning 4 upvotes, #45 of 2026-05-15
  47. Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance 4 upvotes, #45 of 2026-05-15
  48. Quantitative Video World Model Evaluation for Geometric-Consistency 3 upvotes, #48 of 2026-05-15
  49. PreScam: A Benchmark for Predicting Scam Progression from Early Conversations 2 upvotes, #49 of 2026-05-15
  50. LiSA: Lifelong Safety Adaptation via Conservative Policy Induction 2 upvotes, #49 of 2026-05-15
  51. SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks 1 upvotes, #51 of 2026-05-15
  52. Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models 0 upvotes, #52 of 2026-05-15

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.