Daily Papers of 2025-06-16

  1. Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback 53 upvotes, #1 of 2025-06-16
  2. Effective Red-Teaming of Policy-Adherent Agents 37 upvotes, #2 of 2025-06-16
  3. The Diffusion Duality 36 upvotes, #3 of 2025-06-16
  4. Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation 32 upvotes, #4 of 2025-06-16
  5. ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs 20 upvotes, #5 of 2025-06-16
  6. Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache 20 upvotes, #5 of 2025-06-16
  7. LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming? 20 upvotes, #5 of 2025-06-16
  8. Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards 15 upvotes, #8 of 2025-06-16
  9. SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning 14 upvotes, #9 of 2025-06-16
  10. DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO 10 upvotes, #10 of 2025-06-16
  11. JAFAR: Jack up Any Feature at Any Resolution 10 upvotes, #10 of 2025-06-16
  12. Don't Pay Attention 8 upvotes, #12 of 2025-06-16
  13. pLSTM: parallelizable Linear Source Transition Mark networks 8 upvotes, #12 of 2025-06-16
  14. AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions 7 upvotes, #14 of 2025-06-16
  15. SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending 7 upvotes, #14 of 2025-06-16
  16. A High-Quality Dataset and Reliable Evaluation for Interleaved Image-Text Generation 7 upvotes, #14 of 2025-06-16
  17. LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning 7 upvotes, #14 of 2025-06-16
  18. Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings 6 upvotes, #18 of 2025-06-16
  19. A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data 6 upvotes, #18 of 2025-06-16
  20. Learning a Continue-Thinking Token for Enhanced Test-Time Scaling 6 upvotes, #18 of 2025-06-16
  21. Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills 5 upvotes, #21 of 2025-06-16
  22. Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models 5 upvotes, #21 of 2025-06-16
  23. Detecting Harmful Memes with Decoupled Understanding and Guided CoT Reasoning 4 upvotes, #23 of 2025-06-16
  24. Inherently Faithful Attention Maps for Vision Transformers 4 upvotes, #23 of 2025-06-16
  25. Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation 3 upvotes, #25 of 2025-06-16
  26. Reward Models Enable Scalable Code Verification by Trading Accuracy for Throughput 3 upvotes, #25 of 2025-06-16
  27. Configurable Preference Tuning with Rubric-Guided Synthetic Data 2 upvotes, #27 of 2025-06-16

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.