Daily Papers of 2025-09-01

  1. A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code 214 upvotes, #1 of 2025-09-01
  2. A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers 135 upvotes, #2 of 2025-09-01
  3. R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning 105 upvotes, #3 of 2025-09-01
  4. EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control 72 upvotes, #4 of 2025-09-01
  5. Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation 64 upvotes, #5 of 2025-09-01
  6. Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models 23 upvotes, #6 of 2025-09-01
  7. Efficient Code Embeddings from Code Generation Models 18 upvotes, #7 of 2025-09-01
  8. TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis 17 upvotes, #8 of 2025-09-01
  9. TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training 14 upvotes, #9 of 2025-09-01
  10. UItron: Foundational GUI Agent with Advanced Perception and Planning 12 upvotes, #10 of 2025-09-01
  11. AHELM: A Holistic Evaluation of Audio-Language Models 9 upvotes, #11 of 2025-09-01
  12. Model-Task Alignment Drives Distinct RL Outcomes 8 upvotes, #12 of 2025-09-01
  13. CLIPSym: Delving into Symmetry Detection with CLIP 7 upvotes, #13 of 2025-09-01
  14. Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery 5 upvotes, #14 of 2025-09-01
  15. Morae: Proactively Pausing UI Agents for User Choices 5 upvotes, #14 of 2025-09-01
  16. HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation 1 upvotes, #16 of 2025-09-01
  17. Deep Residual Echo State Networks: exploring residual orthogonal connections in untrained Recurrent Neural Networks 1 upvotes, #16 of 2025-09-01
  18. EduRABSA: An Education Review Dataset for Aspect-based Sentiment Analysis Tasks 0 upvotes, #18 of 2025-09-01
  19. Quantization Robustness to Input Degradations for Object Detection 1 upvotes, #18 of 2025-09-01

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.