8 days agoHugging Face Daily PapersPOSS: Position Specialist Generates Better Draft for Speculative Decoding
8 days agoHugging Face Daily PapersRobust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting
8 days agoHugging Face Daily PapersVideo-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning
8 days agoHugging Face Daily PapersDenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
9 days agoHugging Face Daily PapersRefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions
9 days agoHugging Face Daily PapersUnleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem
9 days agoHugging Face Daily PapersIllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation
9 days agoHugging Face Daily PapersUniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
9 days agoHugging Face Daily PapersMERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query