Daily Papers of 2025-08-13

  1. WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent 114 upvotes, #1 of 2025-08-13
  2. Matrix-3D: Omnidirectional Explorable 3D World Generation 67 upvotes, #2 of 2025-08-13
  3. Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL 45 upvotes, #3 of 2025-08-13
  4. Complex Logical Instruction Generation 38 upvotes, #4 of 2025-08-13
  5. CharacterShot: Controllable and Consistent 4D Character Animation 37 upvotes, #5 of 2025-08-13
  6. Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models 34 upvotes, #6 of 2025-08-13
  7. VertexRegen: Mesh Generation with Continuous Level of Detail 33 upvotes, #7 of 2025-08-13
  8. HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches 28 upvotes, #8 of 2025-08-13
  9. OpenCUA: Open Foundations for Computer-Use Agents 25 upvotes, #9 of 2025-08-13
  10. StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation 24 upvotes, #10 of 2025-08-13
  11. Train Long, Think Short: Curriculum Learning for Efficient Reasoning 22 upvotes, #11 of 2025-08-13
  12. Test-Time Reinforcement Learning for GUI Grounding via Region Consistency 20 upvotes, #12 of 2025-08-13
  13. UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation 16 upvotes, #13 of 2025-08-13
  14. Aryabhata: An exam-focused language model for JEE Math 16 upvotes, #13 of 2025-08-13
  15. Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments 16 upvotes, #13 of 2025-08-13
  16. Cut2Next: Generating Next Shot via In-Context Tuning 12 upvotes, #16 of 2025-08-13
  17. Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy 10 upvotes, #17 of 2025-08-13
  18. Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors 10 upvotes, #17 of 2025-08-13
  19. ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants 9 upvotes, #19 of 2025-08-13
  20. Adversarial Video Promotion Against Text-to-Video Retrieval 9 upvotes, #19 of 2025-08-13
  21. AimBot: A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies 9 upvotes, #19 of 2025-08-13
  22. DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition 8 upvotes, #22 of 2025-08-13
  23. AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators 7 upvotes, #23 of 2025-08-13
  24. Technical Report: Full-Stack Fine-Tuning for the Q Programming Language 5 upvotes, #24 of 2025-08-13
  25. GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay 4 upvotes, #25 of 2025-08-13
  26. Optimization-Free Style Transfer for 3D Gaussian Splats 4 upvotes, #25 of 2025-08-13
  27. TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation 3 upvotes, #27 of 2025-08-13
  28. RedDino: A foundation model for red blood cell analysis 2 upvotes, #28 of 2025-08-13
  29. Bridging Theory and Practice in Quantum Game Theory: Optimized Implementation of the Battle of the Sexes with Error Mitigation on NISQ Hardware 2 upvotes, #28 of 2025-08-13
  30. NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations 1 upvotes, #30 of 2025-08-13
  31. WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion 1 upvotes, #30 of 2025-08-13
  32. Putnam-AXIOM: A Functional and Static Benchmark 1 upvotes, #30 of 2025-08-13
  33. BiasGym: Fantastic Biases and How to Find (and Remove) Them 1 upvotes, #30 of 2025-08-13
  34. Improving Masked Style Transfer using Blended Partial Convolution 0 upvotes, #34 of 2025-08-13
  35. Text-conditioned State Space Model For Domain-generalized Change Detection Visual Question Answering 0 upvotes, #34 of 2025-08-13

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.