Daily Papers of 2025-06-11

  1. Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models 70 upvotes, #1 of 2025-06-11
  2. Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better 34 upvotes, #2 of 2025-06-11
  3. RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling 31 upvotes, #3 of 2025-06-11
  4. Seeing Voices: Generating A-Roll Video from Audio with Mirage 25 upvotes, #4 of 2025-06-11
  5. Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models 22 upvotes, #5 of 2025-06-11
  6. Solving Inequality Proofs with Large Language Models 20 upvotes, #6 of 2025-06-11
  7. Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion 18 upvotes, #7 of 2025-06-11
  8. Aligning Text, Images, and 3D Structure Token-by-Token 17 upvotes, #8 of 2025-06-11
  9. Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation 15 upvotes, #9 of 2025-06-11
  10. Squeeze3D: Your 3D Generation Model is Secretly an Extreme Neural Compressor 11 upvotes, #10 of 2025-06-11
  11. ECoRAG: Evidentiality-guided Compression for Long Context RAG 9 upvotes, #11 of 2025-06-11
  12. Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs 8 upvotes, #12 of 2025-06-11
  13. Institutional Books 1.0: A 242B token dataset from Harvard Library's collections, refined for accuracy and usability 8 upvotes, #12 of 2025-06-11
  14. DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs 7 upvotes, #14 of 2025-06-11
  15. Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction 6 upvotes, #15 of 2025-06-11
  16. Mathesis: Towards Formal Theorem Proving from Natural Languages 5 upvotes, #16 of 2025-06-11
  17. MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models 4 upvotes, #17 of 2025-06-11
  18. DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval 4 upvotes, #17 of 2025-06-11
  19. MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Models 3 upvotes, #19 of 2025-06-11
  20. RKEFino1: A Regulation Knowledge-Enhanced Large Language Model 3 upvotes, #19 of 2025-06-11
  21. QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answering 2 upvotes, #21 of 2025-06-11

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.