collaborators

10 papers

cs.CV2025

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…

cs.CV2025

MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs

Yipeng Du, Tiehan Fan, Kepan Nan +6

Despite advancements in Multimodal Large Language Models (MLLMs), their proficiency in fine-grained video motion understanding remains critically limited. They often lack inter-fra…

cs.CV2025

Show-o2: Improved Native Unified Multimodal Models

Jinheng Xie, Zhenheng Yang, Mike Zheng Shou

This paper presents improved native unified multimodal models, \emph{i.e.,} Show-o2, that leverage autoregressive modeling and flow matching. Built upon a 3D causal variational aut…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

Team Seawead, Ceyuan Yang, Zhijie Lin +52

This technical report presents a cost-efficient strategy for training a video generation foundation model. We present a mid-sized research model with approximately 7 billion parame…