Daily Papers of 2026-06-05

  1. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution 86 upvotes, #1 of 2026-06-05
  2. ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? 47 upvotes, #2 of 2026-06-05
  3. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration 44 upvotes, #3 of 2026-06-05
  4. AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints 40 upvotes, #4 of 2026-06-05
  5. VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding 35 upvotes, #5 of 2026-06-05
  6. RobotValues: Evaluating Household Robots When Human Values Conflict 25 upvotes, #6 of 2026-06-05
  7. Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation 25 upvotes, #6 of 2026-06-05
  8. LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing 24 upvotes, #8 of 2026-06-05
  9. Rethinking Continual Experience Internalization for Self-Evolving LLM Agents 23 upvotes, #9 of 2026-06-05
  10. Personal AI Agent for Camera Roll VQA 19 upvotes, #10 of 2026-06-05
  11. MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery 19 upvotes, #10 of 2026-06-05
  12. The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset 18 upvotes, #12 of 2026-06-05
  13. Complexity-Balanced Diffusion Splitting 17 upvotes, #13 of 2026-06-05
  14. Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation? 16 upvotes, #14 of 2026-06-05
  15. Unsupervised Skill Discovery for Agentic Data Analysis 12 upvotes, #15 of 2026-06-05
  16. AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding 10 upvotes, #16 of 2026-06-05
  17. MAOAM: Unified Object and Material Selection with Vision-Language Models 9 upvotes, #17 of 2026-06-05
  18. OPRD: On-Policy Representation Distillation 9 upvotes, #17 of 2026-06-05
  19. World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis 8 upvotes, #19 of 2026-06-05
  20. LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs 8 upvotes, #19 of 2026-06-05
  21. Latent Reasoning with Normalizing Flows 8 upvotes, #19 of 2026-06-05
  22. The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs 7 upvotes, #22 of 2026-06-05
  23. Flash-WAM: Modality-Aware Distillation for World Action Models 7 upvotes, #22 of 2026-06-05
  24. Towards One-to-Many Temporal Grounding 7 upvotes, #22 of 2026-06-05
  25. Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents 6 upvotes, #25 of 2026-06-05
  26. Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction 6 upvotes, #25 of 2026-06-05
  27. Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents 5 upvotes, #27 of 2026-06-05
  28. AdaCodec: A Predictive Visual Code for Video MLLMs 5 upvotes, #27 of 2026-06-05
  29. The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models 5 upvotes, #27 of 2026-06-05
  30. SePO: Self-Evolving Prompt Agent for System Prompt Optimization 5 upvotes, #27 of 2026-06-05
  31. SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction 4 upvotes, #31 of 2026-06-05
  32. Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs 4 upvotes, #31 of 2026-06-05
  33. Benchmark Everything Everywhere All at Once 4 upvotes, #31 of 2026-06-05
  34. Trust Region Q Adjoint Matching 3 upvotes, #34 of 2026-06-05
  35. MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding 3 upvotes, #34 of 2026-06-05
  36. EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management 3 upvotes, #34 of 2026-06-05
  37. Video2LoRA: Parametric Video Internalization for Vision-Language Models 3 upvotes, #34 of 2026-06-05
  38. BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understanding 3 upvotes, #34 of 2026-06-05
  39. Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models 3 upvotes, #34 of 2026-06-05
  40. Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination 2 upvotes, #40 of 2026-06-05
  41. Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning 2 upvotes, #40 of 2026-06-05
  42. Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions 2 upvotes, #40 of 2026-06-05
  43. LLM Anonymization Against Agentic Re-Identification 1 upvotes, #43 of 2026-06-05
  44. Multimodal Music Recommendation System using LLMs 1 upvotes, #43 of 2026-06-05
  45. Quality-Guided Semi-Supervised Learning for Medical Image Segmentation 1 upvotes, #43 of 2026-06-05
  46. Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing 1 upvotes, #43 of 2026-06-05
  47. AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents 1 upvotes, #43 of 2026-06-05
  48. Regret Minimization with Adaptive Opponents in Repeated Games 1 upvotes, #43 of 2026-06-05
  49. ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment 1 upvotes, #49 of 2026-06-05
  50. SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces 2 upvotes, #49 of 2026-06-05

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.