Daily Papers of 2024-11-25

1. TÜLU 3: Pushing Frontiers in Open Language Model Post-Training 55 upvotes, #1 of 2024-11-25
2. OminiControl: Minimal and Universal Control for Diffusion Transformer 41 upvotes, #2 of 2024-11-25
3. Style-Friendly SNR Sampler for Style-Driven Generation 35 upvotes, #3 of 2024-11-25
4. A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection 20 upvotes, #4 of 2024-11-25
5. BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games 17 upvotes, #5 of 2024-11-25
6. MyTimeMachine: Personalized Facial Age Transformation 16 upvotes, #6 of 2024-11-25
7. Large Multi-modal Models Can Interpret Features in Large Multi-modal Models 14 upvotes, #7 of 2024-11-25
8. Novel View Extrapolation with Video Diffusion Priors 10 upvotes, #8 of 2024-11-25
9. Efficient Long Video Tokenization via Coordinated-based Patch Reconstruction 10 upvotes, #8 of 2024-11-25
10. VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection 10 upvotes, #8 of 2024-11-25
11. VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement 8 upvotes, #11 of 2024-11-25
12. WildLMa: Long Horizon Loco-Manipulation in the Wild 6 upvotes, #12 of 2024-11-25
13. Adapting Vision Foundation Models for Robust Cloud Segmentation in Remote Sensing Images 4 upvotes, #13 of 2024-11-25
14. One to rule them all: natural language to bind communication, perception and action 3 upvotes, #14 of 2024-11-25

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.