Daily Papers of 2026-06-03

  1. OCC-RAG: Optimal Cognitive Core for Faithful Question Answering 89 upvotes, #1 of 2026-06-03
  2. KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks 59 upvotes, #2 of 2026-06-03
  3. From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain 52 upvotes, #3 of 2026-06-03
  4. Trust Region On-Policy Distillation 43 upvotes, #4 of 2026-06-03
  5. Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking 38 upvotes, #5 of 2026-06-03
  6. World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning 29 upvotes, #6 of 2026-06-03
  7. Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories 29 upvotes, #6 of 2026-06-03
  8. A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL 27 upvotes, #8 of 2026-06-03
  9. AutoMedBench: Towards Medical AutoResearch with Agentic AI Models 26 upvotes, #9 of 2026-06-03
  10. WALL-WM: Carving World Action Modeling at the Event Joints 23 upvotes, #10 of 2026-06-03
  11. Benchmarking Visual State Tracking in Multimodal Video Understanding 23 upvotes, #10 of 2026-06-03
  12. MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection 22 upvotes, #12 of 2026-06-03
  13. NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation 22 upvotes, #12 of 2026-06-03
  14. Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching 22 upvotes, #12 of 2026-06-03
  15. Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging 21 upvotes, #15 of 2026-06-03
  16. Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning 18 upvotes, #16 of 2026-06-03
  17. TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL 17 upvotes, #17 of 2026-06-03
  18. PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training 15 upvotes, #18 of 2026-06-03
  19. Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation 14 upvotes, #19 of 2026-06-03
  20. Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling 14 upvotes, #19 of 2026-06-03
  21. Ψ-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues 13 upvotes, #21 of 2026-06-03
  22. Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams 12 upvotes, #22 of 2026-06-03
  23. Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models 10 upvotes, #23 of 2026-06-03
  24. Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces 9 upvotes, #24 of 2026-06-03
  25. PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological Maps 9 upvotes, #24 of 2026-06-03
  26. MERIT: Learning Disentangled Music Representations for Audio Similarity 8 upvotes, #26 of 2026-06-03
  27. OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification 8 upvotes, #26 of 2026-06-03
  28. Value-Aware Stochastic KV Cache Eviction for Reasoning Models 8 upvotes, #26 of 2026-06-03
  29. Stateful Visual Encoders for Vision-Language Models 8 upvotes, #26 of 2026-06-03
  30. αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion 7 upvotes, #30 of 2026-06-03
  31. A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems 6 upvotes, #31 of 2026-06-03
  32. Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling 5 upvotes, #32 of 2026-06-03
  33. Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates 5 upvotes, #32 of 2026-06-03
  34. ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree 4 upvotes, #34 of 2026-06-03
  35. GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards 4 upvotes, #34 of 2026-06-03
  36. Prior Availability in Industrial Visual Sim-to-Real: A Review of CAD-Guided and CAD-Unavailable Regimes 3 upvotes, #36 of 2026-06-03
  37. AURA: Action-Gated Memory for Robot Policies at Constant VRAM 3 upvotes, #36 of 2026-06-03
  38. The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development? 3 upvotes, #36 of 2026-06-03
  39. Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations 2 upvotes, #39 of 2026-06-03
  40. AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents 2 upvotes, #39 of 2026-06-03
  41. BA-T: An Iterative Transformer for Two-View Bundle Adjustment 2 upvotes, #39 of 2026-06-03
  42. SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation 2 upvotes, #39 of 2026-06-03

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.