Daily Papers of 2025-04-01

  1. MoCha: Towards Movie-Grade Talking Character Synthesis 103 upvotes, #1 of 2025-04-01
  2. TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes 87 upvotes, #2 of 2025-04-01
  3. Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model 59 upvotes, #3 of 2025-04-01
  4. What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models 49 upvotes, #4 of 2025-04-01
  5. Efficient Inference for Large Reasoning Models: A Survey 45 upvotes, #5 of 2025-04-01
  6. Unicorn: Text-Only Data Synthesis for Vision Language Model Training 37 upvotes, #6 of 2025-04-01
  7. TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization 33 upvotes, #7 of 2025-04-01
  8. RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy 29 upvotes, #8 of 2025-04-01
  9. SketchVideo: Sketch-based Video Generation and Editing 21 upvotes, #9 of 2025-04-01
  10. Effectively Controlling Reasoning Models through Thinking Intervention 18 upvotes, #10 of 2025-04-01
  11. Expanding RL with Verifiable Rewards Across Diverse Domains 17 upvotes, #11 of 2025-04-01
  12. Query and Conquer: Execution-Guided SQL Generation 17 upvotes, #11 of 2025-04-01
  13. Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data 15 upvotes, #13 of 2025-04-01
  14. ActionStudio: A Lightweight Framework for Data and Training of Large Action Models 12 upvotes, #14 of 2025-04-01
  15. TeleAntiFraud-28k: A Audio-Text Slow-Thinking Dataset for Telecom Fraud Detection 11 upvotes, #15 of 2025-04-01
  16. Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code 10 upvotes, #16 of 2025-04-01
  17. AvatarArtist: Open-Domain 4D Avatarization 8 upvotes, #17 of 2025-04-01
  18. Easi3R: Estimating Disentangled Motion from DUSt3R Without Training 7 upvotes, #18 of 2025-04-01
  19. UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation 6 upvotes, #19 of 2025-04-01
  20. MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs 6 upvotes, #19 of 2025-04-01
  21. DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness 5 upvotes, #21 of 2025-04-01
  22. Decoupling Angles and Strength in Low-rank Adaptation 4 upvotes, #22 of 2025-04-01
  23. PAVE: Patching and Adapting Video Large Language Models 4 upvotes, #22 of 2025-04-01
  24. Bridging Evolutionary Multiobjective Optimization and GPU Acceleration via Tensorization 4 upvotes, #22 of 2025-04-01
  25. KOFFVQA: An Objectively Evaluated Free-form VQA Benchmark for Large Vision-Language Models in the Korean Language 4 upvotes, #22 of 2025-04-01
  26. Entropy-Based Adaptive Weighting for Self-Training 4 upvotes, #22 of 2025-04-01
  27. Understanding Co-speech Gestures in-the-wild 1 upvotes, #27 of 2025-04-01

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.