6 papers
Reward Lightning: Fast Video Generation via Homologous Preference Distillation
Jiaxiang Cheng, Bing Ma, Xuhua Ren +4
Achieving simultaneous preference alignment and distillation acceleration in video diffusion models remains an open challenge. Existing methods optimize the two objectives over mis…
Implicit Preference Alignment for Human Image Animation
Yuanzhi Wang, Xuhua Ren, Jiaxiang Cheng +5
Human image animation has witnessed significant advancements, yet generating high-fidelity hand motions remains a persistent challenge due to their high degrees of freedom and moti…
FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
Yuanzhi Wang, Xuhua Ren, Jiaxiang Cheng +7
Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Despite recent progress, existi…
Phased One-Step Adversarial Equilibrium for Video Diffusion Models
Jiaxiang Cheng, Bing Ma, Xuhua Ren +7
Video diffusion generation suffers from critical sampling efficiency bottlenecks, particularly for large-scale models and long contexts. Existing video acceleration methods, adapte…
Beyond Reward Margin: Rethinking and Resolving Likelihood Displacement in Diffusion Models via Video Generation
Ruojun Xu, Yu Kai, Xuhua Ren +4
Direct Preference Optimization (DPO) has shown promising results in aligning generative outputs with human preferences by distinguishing between chosen and rejected samples. Howeve…
PersonaVlog: Personalized Multimodal Vlog Generation with Multi-Agent Collaboration and Iterative Self-Correction
Xiaolu Hou, Bing Ma, Jiaxiang Cheng +5
With the growing demand for short videos and personalized content, automated Video Log (Vlog) generation has become a key direction in multimodal content creation. Existing methods…