Daily Papers of 2026-06-17

  1. Looped World Models 457 upvotes, #1 of 2026-06-17
  2. LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling 203 upvotes, #2 of 2026-06-17
  3. Learning from the Self-future: On-policy Self-distillation for dLLMs 74 upvotes, #3 of 2026-06-17
  4. Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients 60 upvotes, #4 of 2026-06-17
  5. GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine? 55 upvotes, #5 of 2026-06-17
  6. ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining 49 upvotes, #6 of 2026-06-17
  7. LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching 39 upvotes, #7 of 2026-06-17
  8. TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs 30 upvotes, #8 of 2026-06-17
  9. OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation 27 upvotes, #9 of 2026-06-17
  10. Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion 21 upvotes, #10 of 2026-06-17
  11. Text-Vision Co-Instructed Image Editing 19 upvotes, #11 of 2026-06-17
  12. Rethinking the Role of Efficient Attention in Hybrid Architectures 17 upvotes, #12 of 2026-06-17
  13. Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus 16 upvotes, #13 of 2026-06-17
  14. Self-Evolving Visual Questioner 15 upvotes, #14 of 2026-06-17
  15. EgoCS-400K: An Egocentric Gameplay Dataset for World Models 15 upvotes, #14 of 2026-06-17
  16. Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification 14 upvotes, #16 of 2026-06-17
  17. Variable-Width Transformers 13 upvotes, #17 of 2026-06-17
  18. Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion 11 upvotes, #18 of 2026-06-17
  19. RefGC-SR^2: Reference-guided Generated Content Super-Resolution and Refinement 9 upvotes, #19 of 2026-06-17
  20. ProCUA-SFT Technical Report 9 upvotes, #19 of 2026-06-17
  21. A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization 8 upvotes, #21 of 2026-06-17
  22. ActWorld: From Explorable to Interactive World Model via Action-Aware Memory 8 upvotes, #21 of 2026-06-17
  23. ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions 8 upvotes, #21 of 2026-06-17
  24. Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences 7 upvotes, #24 of 2026-06-17
  25. Aligning Quantum Operators with Large Language Models 4 upvotes, #25 of 2026-06-17
  26. MotionVLA: Vision-Language-Action Model for Humanoid Motion 4 upvotes, #25 of 2026-06-17
  27. Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning 4 upvotes, #25 of 2026-06-17
  28. RepSelect: Robust LLM Unlearning via Representation Selectivity 4 upvotes, #25 of 2026-06-17
  29. Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings 3 upvotes, #29 of 2026-06-17
  30. The Price of Anarchy in Disaggregated Inference 1 upvotes, #30 of 2026-06-17
  31. Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems 1 upvotes, #30 of 2026-06-17

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.