Xin Liu

EmotionHallucer: Evaluating Emotion Hallucinations in Multimodal Large Language Models

Zero-Shot Video Restoration and Enhancement with Assistance of Video Diffusion Models

Denoising and Alignment: Rethinking Domain Generalization for Multimodal Face Anti-Spoofing

VC-VAE: Enhancing Video VAE with Video Codec Standard for Latent Video Diffusion Model

Token-by-Token Election: Improving Language Model Reasoning through Token-Level Multi-model Collaboration