Daily Papers of 2024-12-24

  1. RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response 80 upvotes, #1 of 2024-12-24
  2. B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners 38 upvotes, #2 of 2024-12-24
  3. Diving into Self-Evolving Training for Multimodal Reasoning 37 upvotes, #3 of 2024-12-24
  4. Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching 32 upvotes, #4 of 2024-12-24
  5. OpenAI o1 System Card 27 upvotes, #5 of 2024-12-24
  6. Deliberation in Latent Space via Differentiable Cache Augmentation 26 upvotes, #6 of 2024-12-24
  7. Revisiting In-Context Learning with Long Context Language Models 23 upvotes, #7 of 2024-12-24
  8. Large Motion Video Autoencoding with Cross-modal Video VAE 22 upvotes, #8 of 2024-12-24
  9. LearnLM: Improving Gemini for Learning 17 upvotes, #9 of 2024-12-24
  10. DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought 17 upvotes, #9 of 2024-12-24
  11. Outcome-Refining Process Supervision for Code Generation 16 upvotes, #11 of 2024-12-24
  12. PC Agent: While You Sleep, AI Works -- A Cognitive Journey into Digital World 10 upvotes, #12 of 2024-12-24
  13. ResearchTown: Simulator of Human Research Community 10 upvotes, #12 of 2024-12-24
  14. Agent-SafetyBench: Evaluating the Safety of LLM Agents 8 upvotes, #14 of 2024-12-24
  15. Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding 8 upvotes, #14 of 2024-12-24
  16. NILE: Internal Consistency Alignment in Large Language Models 6 upvotes, #16 of 2024-12-24
  17. OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning 5 upvotes, #17 of 2024-12-24

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.