8 papers
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
Yuchao Gu, Guian Fang, Yuxin Jiang +4
Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling step…
Mitty: Diffusion-based Human-to-Robot Video Generation
Yiren Song, Cheng Liu, Weijia Mao +1
Learning directly from human demonstration videos is a key milestone toward scalable and generalizable robot learning. Yet existing methods rely on intermediate representations suc…
The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
Weijia Mao, Hao Chen, Zhenheng Yang +1
A reliable reward function is essential for reinforcement learning (RL) in image generation. Most current RL approaches depend on pre-trained preference models that output scalar r…
Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
Jinheng Xie, Weijia Mao, Zechen Bai +7
We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discret…
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
Weijia Mao, Zhenheng Yang, Mike Zheng Shou
Unified multimodal large language models such as Show-o and Janus have achieved strong performance across both generation and understanding tasks. However, these models typically r…
Long-Context Autoregressive Video Modeling with Next-Frame Prediction
Yuchao Gu, Weijia Mao, Mike Zheng Shou
Long-context video modeling is essential for enabling generative models to function as world simulators, as they must maintain temporal coherence over extended time spans. However,…