8 papers
DreamStream: Towards Policy-Oriented Generative Simulation for End-to-End Driving
Ziyang Leng, Sicheng Mo, Seth Z. Zhao +4
Faithfully evaluating end-to-end driving policies in simulation requires observations that are not merely photo-realistic, but preserve the scene features a policy relies on to mak…
Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers
Sicheng Mo, Yuheng Li, Ziyang Leng +2
Multi-agent interactive world models should not only generate consistent observations, but also maintain world states that persist across agents and evolve across views. Existing a…
UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation
Lin Zhang, Sicheng Mo, Zefan Cai +6
Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. However, existing methods…
Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaboration
Sicheng Mo, Thao Nguyen, Richard Zhang +7
In this work, we explore an untapped signal in diffusion model inference. While all previous methods generate images independently at inference, we instead ask if samples can be ge…
Relational Visual Similarity
Thao Nguyen, Sicheng Mo, Krishna Kumar Singh +6
Humans do not just see attribute similarity -- we also see relational similarity. An apple is like a peach because both are reddish fruit, but the Earth is also like a peach: its c…
Dreamland: Controllable World Creation with Simulator and Generative Models
Sicheng Mo, Ziyang Leng, Leon Liu +3
Large-scale video generative models can synthesize diverse and realistic visual content for dynamic world creation, but they often lack element-wise controllability, hindering thei…
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…
SimGen: Simulator-conditioned Driving Scene Generation
Yunsong Zhou, Michael Simon, Zhenghao Peng +4
Controllable synthetic data generation can substantially lower the annotation cost of training data. Prior works use diffusion models to generate driving images conditioned on the…