Daily Papers of 2025-08-27

  1. VibeVoice Technical Report 118 upvotes, #1 of 2025-08-27
  2. TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling 76 upvotes, #2 of 2025-08-27
  3. CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics 46 upvotes, #3 of 2025-08-27
  4. VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space 39 upvotes, #4 of 2025-08-27
  5. OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation 38 upvotes, #5 of 2025-08-27
  6. Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels 34 upvotes, #6 of 2025-08-27
  7. UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning 34 upvotes, #6 of 2025-08-27
  8. Spacer: Towards Engineered Scientific Inspiration 31 upvotes, #8 of 2025-08-27
  9. Autoregressive Universal Video Segmentation Model 26 upvotes, #9 of 2025-08-27
  10. CineScale: Free Lunch in High-Resolution Cinematic Visual Generation 19 upvotes, #10 of 2025-08-27
  11. Wan-S2V: Audio-Driven Cinematic Video Generation 16 upvotes, #11 of 2025-08-27
  12. ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models 14 upvotes, #12 of 2025-08-27
  13. FastMesh:Efficient Artistic Mesh Generation via Component Decoupling 14 upvotes, #12 of 2025-08-27
  14. ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks 13 upvotes, #14 of 2025-08-27
  15. DrugReasoner: Interpretable Drug Approval Prediction with a Reasoning-augmented Language Model 13 upvotes, #14 of 2025-08-27
  16. Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks 9 upvotes, #16 of 2025-08-27
  17. Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering 6 upvotes, #17 of 2025-08-27
  18. ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models 6 upvotes, #17 of 2025-08-27
  19. MovieCORE: COgnitive REasoning in Movies 5 upvotes, #19 of 2025-08-27
  20. Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning 5 upvotes, #19 of 2025-08-27
  21. QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting 3 upvotes, #21 of 2025-08-27
  22. Training Language Model Agents to Find Vulnerabilities with CTF-Dojo 3 upvotes, #21 of 2025-08-27
  23. Steering When Necessary: Flexible Steering Large Language Models with Backtracking 2 upvotes, #23 of 2025-08-27
  24. Unraveling the cognitive patterns of Large Language Models through module communities 2 upvotes, #23 of 2025-08-27
  25. Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills 1 upvotes, #25 of 2025-08-27
  26. ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation 0 upvotes, #26 of 2025-08-27
  27. Forecasting Probability Distributions of Financial Returns with Deep Neural Networks 0 upvotes, #26 of 2025-08-27

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.