ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL Paper โข 2505.24875 โข Published May 30 โข 10
World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning Paper โข 2503.10480 โข Published Mar 13 โข 54
Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models Paper โข 2410.02416 โข Published Oct 3, 2024 โข 33
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper โข 2502.14786 โข Published Feb 20 โข 146