Daily Papers of 2026-06-10

  1. ABot-Earth 0.5: Generative 3D Earth Model 470 upvotes, #1 of 2026-06-10
  2. Kwai Keye-VL-2.0 Technical Report 185 upvotes, #2 of 2026-06-10
  3. Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories 110 upvotes, #3 of 2026-06-10
  4. Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution 76 upvotes, #4 of 2026-06-10
  5. Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts 52 upvotes, #5 of 2026-06-10
  6. SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research 50 upvotes, #6 of 2026-06-10
  7. SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning 43 upvotes, #7 of 2026-06-10
  8. Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning 42 upvotes, #8 of 2026-06-10
  9. Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models 41 upvotes, #9 of 2026-06-10
  10. MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism 38 upvotes, #10 of 2026-06-10
  11. Rethinking the Divergence Regularization in LLM RL 33 upvotes, #11 of 2026-06-10
  12. Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization 33 upvotes, #11 of 2026-06-10
  13. WorldOlympiad: Can Your World Model Survive a Triathlon? 31 upvotes, #13 of 2026-06-10
  14. ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations 26 upvotes, #14 of 2026-06-10
  15. Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields 21 upvotes, #15 of 2026-06-10
  16. EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents 18 upvotes, #16 of 2026-06-10
  17. One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA 16 upvotes, #17 of 2026-06-10
  18. Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It 16 upvotes, #17 of 2026-06-10
  19. Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders 12 upvotes, #19 of 2026-06-10
  20. Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval 11 upvotes, #20 of 2026-06-10
  21. SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction 10 upvotes, #21 of 2026-06-10
  22. BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling 8 upvotes, #22 of 2026-06-10
  23. Bridging the Agent-World Gap: Text World Models for LLM-based Agents 7 upvotes, #23 of 2026-06-10
  24. PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models 7 upvotes, #23 of 2026-06-10
  25. How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs 6 upvotes, #25 of 2026-06-10
  26. Next Forcing: Causal World Modeling with Multi-Chunk Prediction 6 upvotes, #25 of 2026-06-10
  27. What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems 5 upvotes, #27 of 2026-06-10
  28. Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests 5 upvotes, #27 of 2026-06-10
  29. Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking 5 upvotes, #27 of 2026-06-10
  30. MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation 5 upvotes, #27 of 2026-06-10
  31. Dynamic Linear Attention 5 upvotes, #27 of 2026-06-10
  32. UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors 5 upvotes, #27 of 2026-06-10
  33. IR3DE: A Linear Router for Large Language Models 4 upvotes, #33 of 2026-06-10
  34. Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating 4 upvotes, #33 of 2026-06-10
  35. U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training 4 upvotes, #33 of 2026-06-10
  36. Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation 3 upvotes, #36 of 2026-06-10
  37. Decentralized Multi-Agent Systems with Shared Context 3 upvotes, #36 of 2026-06-10
  38. Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning 3 upvotes, #36 of 2026-06-10
  39. The Role of Feedback Alignment in Self-Distillation 3 upvotes, #36 of 2026-06-10
  40. On the Limits of LLM-as-Judge for Scientific Novelty Assessment 3 upvotes, #36 of 2026-06-10
  41. PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf 2 upvotes, #41 of 2026-06-10
  42. When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models 2 upvotes, #41 of 2026-06-10
  43. When Behavioral Safety Evaluation Fails: A Representation-Level Perspective 1 upvotes, #43 of 2026-06-10
  44. In-Context Multiple Instance Learning 0 upvotes, #44 of 2026-06-10
  45. BenSyc: Benchmarking Conversational Sycophancy and Human Alignment in LLMs for Bengali Contexts 1 upvotes, #44 of 2026-06-10
  46. FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion 0 upvotes, #44 of 2026-06-10

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.