Daily Papers of 2025-03-31

  1. AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation 75 upvotes, #1 of 2025-03-31
  2. Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback 43 upvotes, #2 of 2025-03-31
  3. A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond 39 upvotes, #3 of 2025-03-31
  4. Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation 34 upvotes, #4 of 2025-03-31
  5. OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning 26 upvotes, #5 of 2025-03-31
  6. ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation 22 upvotes, #6 of 2025-03-31
  7. Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics 21 upvotes, #7 of 2025-03-31
  8. Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency 20 upvotes, #8 of 2025-03-31
  9. ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback 20 upvotes, #8 of 2025-03-31
  10. Your ViT is Secretly an Image Segmentation Model 18 upvotes, #10 of 2025-03-31
  11. Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion Model 17 upvotes, #11 of 2025-03-31
  12. PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving 16 upvotes, #12 of 2025-03-31
  13. Segment Any Motion in Videos 15 upvotes, #13 of 2025-03-31
  14. A Refined Analysis of Massive Activations in LLMs 13 upvotes, #14 of 2025-03-31
  15. Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging 10 upvotes, #15 of 2025-03-31
  16. 4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding 8 upvotes, #16 of 2025-03-31
  17. SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling 7 upvotes, #17 of 2025-03-31
  18. Reconstructing Humans with a Biomechanically Accurate Skeleton 7 upvotes, #17 of 2025-03-31
  19. MedAgent-Pro: Towards Multi-modal Evidence-based Medical Diagnosis via Reasoning Agentic Workflow 6 upvotes, #19 of 2025-03-31
  20. On Large Multimodal Models as Open-World Image Classifiers 5 upvotes, #20 of 2025-03-31
  21. Challenges and Paths Towards AI for Software Engineering 3 upvotes, #21 of 2025-03-31
  22. SWI: Speaking with Intent in Large Language Models 2 upvotes, #22 of 2025-03-31
  23. X^{2}-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction 2 upvotes, #22 of 2025-03-31

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.