Zhen Luo

I am a third-year Ph.D. student jointly affiliated with the Shanghai Innovation Institute (SII) and the Southern University of Science and Technology (SUSTech), co-advised by Prof. Yanwei Fu and Prof. Feng Zheng.

My research focuses on generative simulation and multimodal world models for embodied intelligence.

Generative simulation for embodied AI: creating scalable, simulation-ready 3D environments and interactive assets for robot learning and evaluation.

Multimodal world models: developing predictive models of physical interactions from vision, touch, language, and action for contact-rich manipulation and planning.

Contact: Email / Google Scholar

Portrait of Zhen Luo

Education

News

Publications

(* denotes equal contribution)

DreamTraj 6-DoF trajectory generation
DreamTraj: Generating 6-DoF Object Trajectories by Reading Unrendered Video Diffusion Latents
Tongsheng Ding*, Zhen Luo*, Yixuan Yang*, Boyu Wang, Luyang Xie, Jinyu Yang, Feng Zheng
arXiv preprint, 2026
[project] [paper]
STABLE tabletop scene generation results
STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System
Zhen Luo*, Yixuan Yang*, Xudong Xu, Jinkun Hao, Zhaoyang Lyu, Feng Zheng, Jiangmiao Pang, Yanwei Fu
International Conference on Machine Learning (ICML), 2026
[project] [paper]
Code-as-Room 3D room generation results
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
Yixuan Yang*, Zhen Luo*, Wanshui Gan*, Jinkun Hao, Junru Lu, Jinghao Yan, Zhaoyang Lyu, Xudong Xu
arXiv preprint, 2026
[project] [paper] [code]
ArtiWorld LLM-driven articulation
ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes
Yixuan Yang*, Luyang Xie*, Zhen Luo*, Zixiang Zhao, Tongsheng Ding, Mingqi Gao, Feng Zheng
ACM International Conference on Multimedia (ACM MM), 2026
[paper]
MesaTask generated 3D tabletop scenes
MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning
Jinkun Hao*, Naifu Liang*, Zhen Luo*, Xudong Xu, Weipeng Zhong, Ran Yi, Yichen Jin, Zhaoyang Lyu, Feng Zheng, Lizhuang Ma, Jiangmiao Pang
Advances in Neural Information Processing Systems (NeurIPS), 2025 (Spotlight)
[project] [paper] [code]
OptiScene indoor layout generation
OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization
Yixuan Yang*, Zhen Luo*, Tongsheng Ding*, Junru Lu, Mingqi Gao, Jinyu Yang, Victor Sanchez, Feng Zheng
Advances in Neural Information Processing Systems (NeurIPS), 2025
[project] [paper]
LLplace embodied layout synthesis
LLplace: Embodied 3D Indoor Layout Synthesis Framework with Large Language Model
Yixuan Yang, Junru Lu, Zixiang Zhao, Zhen Luo, Wanxi Dong, Victor Sanchez, Feng Zheng
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025
[paper]
RoboReflect robotic grasping
RoboReflect: Robotic Reflective Reasoning for Grasping Ambiguous-Condition Objects
Zhen Luo, Yixuan Yang, Chang Cai, Yanfu Zhang, Feng Zheng
arXiv 2025
[paper]
InfiniteWorld simulation framework
InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction
Pengzhen Ren*, Min Li*, Zhen Luo*, Xinshuai Song*, Ziwei Chen*, Weijia Liufu*, Yixuan Yang*, et al.
arXiv 2024
[paper] [code]
milliFlow scene flow estimation
milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing
Fangqiang Ding, Zhen Luo, Peijun Zhao, Chris Xiaoxuan Lu
European Conference on Computer Vision (ECCV), 2024
[paper] [code]