BesiegeField
Language-model agents build machines as programs and refine them through physical simulation.
Understand.
Create.
We study generative models, 3D reasoning, and how learning systems interact with the physical world.
Selected research
Scroll horizontally to explore projects. With this list focused, use the left and right arrow keys, or Home and End.
EVA
Aligning video world models with actions a robot can execute.
DrPO
Aligning one-step image generators with preferences without differentiating through rewards.
PAct
From a single image to a 3D object with parts that move.
VGG-Flow
Aligning generative flow models with rewards while preserving their learned priors.
ASAP
Reducing anatomical errors in generated human images through synthetic, localized preferences.
MeshDiffusion
Generating detailed 3D meshes directly with diffusion models.
G-Shell
Reconstructing and generating 3D shapes, from solid objects to thin, open surfaces.
Team
Zhen Liu
Principal Investigator
Wenqian Zhang
PhD student
Zhou Jiang
PhD student
Jinming Ren
MPhil student
Yaocheng Guo
Master’s student
Xiangwei Shen
Master’s student
Zihao Zhou
Undergraduate
Zhuoran Xia
Undergraduate
Jinlong Yang
Undergraduate
Zigeng Xu
Undergraduate
External collaborators
Weiyang Liu
CUHK
Yandong Wen
Westlake University
Yuliang Xiu
Westlake University
Jie Fu
iQuestLab