Daily Papers of 2025-05-01

  1. Sadeed: Advancing Arabic Diacritization Through Small Language Model 54 upvotes, #1 of 2025-05-01
  2. WebThinker: Empowering Large Reasoning Models with Deep Research Capability 41 upvotes, #2 of 2025-05-01
  3. Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math 37 upvotes, #3 of 2025-05-01
  4. Phi-4-reasoning Technical Report 35 upvotes, #4 of 2025-05-01
  5. 100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models 29 upvotes, #5 of 2025-05-01
  6. Softpick: No Attention Sink, No Massive Activations with Rectified Softmax 25 upvotes, #6 of 2025-05-01
  7. COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning 24 upvotes, #7 of 2025-05-01
  8. Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think 21 upvotes, #8 of 2025-05-01
  9. Generative AI for Character Animation: A Comprehensive Survey of Techniques, Applications, and Future Directions 15 upvotes, #9 of 2025-05-01
  10. Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report 15 upvotes, #9 of 2025-05-01
  11. ReVision: High-Quality, Low-Cost Video Generation with Explicit 3D Physics Modeling for Complex Motion and Interaction 12 upvotes, #11 of 2025-05-01
  12. RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning 9 upvotes, #12 of 2025-05-01
  13. Taming the Titans: A Survey of Efficient LLM Inference Serving 9 upvotes, #12 of 2025-05-01
  14. UniBiomed: A Universal Foundation Model for Grounded Biomedical Image Interpretation 4 upvotes, #14 of 2025-05-01
  15. Selecting Optimal Candidate Profiles in Adversarial Environments Using Conjoint Analysis and Machine Learning 3 upvotes, #15 of 2025-05-01

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.