Daily Papers of 2025-01-09

  1. rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking 225 upvotes, #1 of 2025-01-09
  2. Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though 81 upvotes, #2 of 2025-01-09
  3. Agent Laboratory: Using LLM Agents as Research Assistants 76 upvotes, #3 of 2025-01-09
  4. Search-o1: Agentic Search-Enhanced Large Reasoning Models 75 upvotes, #4 of 2025-01-09
  5. URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics 48 upvotes, #5 of 2025-01-09
  6. LLM4SR: A Survey on Large Language Models for Scientific Research 33 upvotes, #6 of 2025-01-09
  7. InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection 22 upvotes, #7 of 2025-01-09
  8. GeAR: Generation Augmented Retrieval 21 upvotes, #8 of 2025-01-09
  9. Chirpy3D: Continuous Part Latents for Creative 3D Bird Generation 17 upvotes, #9 of 2025-01-09
  10. SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images 16 upvotes, #10 of 2025-01-09
  11. DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization 11 upvotes, #11 of 2025-01-09
  12. Multi-task retriever fine-tuning for domain-specific and efficient RAG 10 upvotes, #12 of 2025-01-09
  13. EpiCoder: Encompassing Diversity and Complexity in Code Generation 9 upvotes, #13 of 2025-01-09

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.