Yu Liu

Blend-Aware Latent Diffusion: Mitigating Stitched Seams in Image Inpainting

VividFace: A Robost and High-Fidelity Video Face Swapping Framework

SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction

MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines

EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM

Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic Perspective

ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze

See Further When Clear: Adaptive Generative Modeling with Curriculum Consistency Model