Daily Papers of 2026-06-11

  1. Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models 143 upvotes, #1 of 2026-06-11
  2. Toward Generalist Autonomous Research via Hypothesis-Tree Refinement 112 upvotes, #2 of 2026-06-11
  3. Redesign Mixture-of-Experts Routers with Manifold Power Iteration 86 upvotes, #3 of 2026-06-11
  4. Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks 66 upvotes, #4 of 2026-06-11
  5. Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application 64 upvotes, #5 of 2026-06-11
  6. Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions 59 upvotes, #6 of 2026-06-11
  7. TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders 50 upvotes, #7 of 2026-06-11
  8. DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch 33 upvotes, #8 of 2026-06-11
  9. Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning 30 upvotes, #9 of 2026-06-11
  10. World Pilot: Steering Vision-Language-Action Models with World-Action Priors 25 upvotes, #10 of 2026-06-11
  11. On Subquadratic Architectures: From Applications to Principles 23 upvotes, #11 of 2026-06-11
  12. InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning 22 upvotes, #12 of 2026-06-11
  13. Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling 21 upvotes, #13 of 2026-06-11
  14. ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics 19 upvotes, #14 of 2026-06-11
  15. TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning 18 upvotes, #15 of 2026-06-11
  16. Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code 18 upvotes, #15 of 2026-06-11
  17. Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models 18 upvotes, #15 of 2026-06-11
  18. DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning 16 upvotes, #18 of 2026-06-11
  19. ICA Lens: Interpreting Language Models Without Training Another Dictionary 15 upvotes, #19 of 2026-06-11
  20. i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models 13 upvotes, #20 of 2026-06-11
  21. World Model Self-Distillation: Training World Models to Solve General Tasks 13 upvotes, #20 of 2026-06-11
  22. EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning 11 upvotes, #22 of 2026-06-11
  23. Breaking the Bubble: Asynchronous Pipeline Parallel Training with Bounded Weight Inconsistency 8 upvotes, #23 of 2026-06-11
  24. Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization 7 upvotes, #24 of 2026-06-11
  25. RepWAM: World Action Modeling with Representation Visual-Action Tokenizers 6 upvotes, #25 of 2026-06-11
  26. DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models 5 upvotes, #26 of 2026-06-11
  27. ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction 4 upvotes, #27 of 2026-06-11
  28. POISE: Position-Aware Undetectable Skill Injection on LLM Agents 4 upvotes, #27 of 2026-06-11
  29. Distilling LLM Feedback for Lean Theorem Proving 3 upvotes, #29 of 2026-06-11
  30. Large Language Models Are Overconfident in Their Own Responses 3 upvotes, #29 of 2026-06-11
  31. SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference 3 upvotes, #29 of 2026-06-11
  32. Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training 3 upvotes, #29 of 2026-06-11
  33. Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation 3 upvotes, #29 of 2026-06-11
  34. Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs 3 upvotes, #29 of 2026-06-11
  35. Can Generalist Agents Automate Data Curation? 2 upvotes, #35 of 2026-06-11
  36. Towards Diverse Scientific Hypothesis Search with Large Language Models 2 upvotes, #35 of 2026-06-11
  37. Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay 2 upvotes, #35 of 2026-06-11
  38. Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models 2 upvotes, #35 of 2026-06-11
  39. FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matching 1 upvotes, #39 of 2026-06-11
  40. τ-Rec: A Verifiable Benchmark for Agentic Recommender Systems 1 upvotes, #39 of 2026-06-11
  41. Building Social World Models with Large Language Models 1 upvotes, #39 of 2026-06-11
  42. APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations 1 upvotes, #39 of 2026-06-11

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.