collaborators

5 papers

cs.CV2025

MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training

Haotian Xue, Qi Chen, Zhonghao Wang +4

Video diffusion models achieve strong frame-level fidelity but still struggle with motion coherence, dynamics and realism, often producing jitter, ghosting, or implausible dynamics…

cs.CV2025

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

Xun Huang, Zhengqi Li, Guande He +2

We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models. It addresses the longstanding issue of exposure bias, where models trained on ground…

cs.CV2025

Long-Context State-Space Video World Models

Ryan Po, Yotam Nitzan, Richard Zhang +5

Video diffusion models have recently shown promise for world modeling through autoregressive frame prediction conditioned on actions. However, they struggle to maintain long-term m…

cs.CV2025

X-Fusion: Introducing New Modality to Frozen Large Language Models

Sicheng Mo, Thao Nguyen, Xun Huang +9

We propose X-Fusion, a framework that extends pretrained Large Language Models (LLMs) for multimodal tasks while preserving their language capabilities. X-Fusion employs a dual-tow…

cs.CV2024

From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

Tianwei Yin, Qiang Zhang, Richard Zhang +4

Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a singl…