Daily Papers of 2025-01-23

1. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 271 upvotes, #1 of 2025-01-23
2. Kimi k1.5: Scaling Reinforcement Learning with LLMs 76 upvotes, #2 of 2025-01-23
3. VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding 75 upvotes, #3 of 2025-01-23
4. FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces 62 upvotes, #4 of 2025-01-23
5. Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback 50 upvotes, #5 of 2025-01-23
6. Autonomy-of-Experts Models 38 upvotes, #6 of 2025-01-23
7. O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning 20 upvotes, #7 of 2025-01-23
8. Pairwise RM: Perform Best-of-N Sampling with Knockout Tournament 18 upvotes, #8 of 2025-01-23
9. Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass 14 upvotes, #9 of 2025-01-23
10. IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems 12 upvotes, #10 of 2025-01-23

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.