Daily Papers of 2025-01-13

1. Enabling Scalable Oversight via Self-Evolving Critic 66 upvotes, #1 of 2025-01-13
2. VideoRAG: Retrieval-Augmented Generation over Video Corpus 65 upvotes, #2 of 2025-01-13
3. LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs 57 upvotes, #3 of 2025-01-13
4. OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints 49 upvotes, #4 of 2025-01-13
5. OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding? 36 upvotes, #5 of 2025-01-13
6. Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models 28 upvotes, #6 of 2025-01-13
7. Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains 19 upvotes, #7 of 2025-01-13
8. ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning 15 upvotes, #8 of 2025-01-13
9. ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding 14 upvotes, #9 of 2025-01-13
10. Generative AI for Cel-Animation: A Survey 13 upvotes, #10 of 2025-01-13
11. Infecting Generative AI With Viruses 12 upvotes, #11 of 2025-01-13
12. Multi-subject Open-set Personalization in Video Generation 12 upvotes, #11 of 2025-01-13
13. Demystifying Domain-adaptive Post-training for Financial LLMs 10 upvotes, #13 of 2025-01-13

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.