Zhenggang Tang

唐正纲

I am a Research Scientist at Luma AI, building self-evolving robotic systems. Previously, I worked on unified generation, 3D reconstruction, reinforcement learning, and multi-agent systems. I earned my Ph.D. in Computer Science from the University of Illinois Urbana-Champaign in September 2026, advised by Alexander Schwing. Before that, I received my B.S. from the School of EECS at Peking University.

Email Scholar ↗GitHub ↗LinkedIn ↗

Self-evolving systemsMultimodal foundation models3D reconstruction & generationReinforcement learning

Research & publications

PreprintUnder submission3D generation

Autoregressive Diffusion Modeling for Compositional Text-to-3D Generation

Zhenggang Tang*, Yuehao Wang*, Yuchen Fan, Jun-Kun Chen, Yu-Ying Yeh, Kihyuk Sohn, Zhangyang Wang, Qixing Huang, Rakesh Ranjan, Dilin Wang, Zhicheng Yan

Paper

CVPR 2025Oral3D reconstruction

MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views in 2 Seconds

Zhenggang Tang, Yuchen Fan, Dilin Wang, Hongyu Xu, Rakesh Ranjan, Alex Schwing, Zhicheng Yan

Paper Project Code Video

ICML 2026Multimodal reasoning

Spatio-Temporal LLM: Reasoning about Environments and Actions

Haozhen Zheng, Beitong Tian, Mingyuan Wu, Zhenggang Tang, Klara Nahrstedt, Alex Schwing

Paper

CVPR 2025 WorkshopMulti-view generation

Pixel-Aligned Multi-View Generation with Depth Guided Decoder

Zhenggang Tang, Peiye Zhuang, Chaoyang Wang, Aliaksandr Siarohin, Yash Kant, Alexander Schwing, Sergey Tulyakov, Hsin-Ying Lee

Paper

CVPR 20243D scene editing

NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows

Zhenggang Tang, Zhongzheng Ren, Xiaoming Zhao, Bowen Wen, Jonathan Tremblay, Stan Birchfield, Alexander Schwing

Paper Project

KDD 2023Multi-agent learning

Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance

Yuchen Fang*, Zhenggang Tang*, Kan Ren, Weiqing Liu, Li Zhao, Jiang Bian, Dongsheng Li, Weinan Zhang, Yong Yu, Tie-Yan Liu

Paper

ICRA 2023Robotics & reconstruction

RGB-Only Reconstruction of Tabletop Scenes for Collision-Free Manipulator Control

Zhenggang Tang, Balakumar Sundaralingam, Jonathan Tremblay, Bowen Wen, Ye Yuan, Stephen Tyree, Charles Loop, Alexander Schwing, Stan Birchfield

Paper Project

ICLR 2021Reinforcement learning

Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization

Zhenggang Tang*, Chao Yu*, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Shaolei Du, Yu Wang, Yi Wu

Paper Project

Preprint 2021Multi-agent simulation

A Microscopic Pandemic Simulator for Pandemic Prediction Using Scalable Million-Agent Reinforcement Learning

Zhenggang Tang*, Kai Yan*, Liting Sun, Wei Zhan, Changliu Liu

Paper

* Equal contribution. Full publication record on Google Scholar ↗.

Experience

Luma AI
Currently
Research Scientist
Meta
2024 – 2025
Research Scientist Intern · XR Tech Core AI
May 2025 – Dec 2025 · May 2024 – Jan 2025
Snap
Jan – May 2024
Research Scientist Intern · Creative Vision Group
NVIDIA
May – Oct 2022
Research Scientist Intern
Microsoft Research Asia
Oct 2020 – May 2021
Research Scientist Intern · Fintech Group
Tsinghua University
Nov 2019 – May 2020
Institute for Interdisciplinary Information Sciences
Mentored by Yi Wu

Education

University of Illinois Urbana-Champaign

Ph.D. in Computer Science

Advisor: Alexander Schwing

Aug 2021 – Sep 2026

Peking University

B.S. in Computer Science · Summa Cum Laude

2017 – 2021

Academic service

Reviewer for CVPR, ECCV, NeurIPS, ICLR, 3DV, and SIGGRAPH Asia.

Honors

Gold Medal · APIO 2016
Asia-Pacific Informatics Olympiad (China District)

Silver Medal · NOI 2016
National Olympiad in Informatics

Zhenggang Tang

Research & publications

Experience

Luma AI

Meta

Snap

NVIDIA

Microsoft Research Asia

Tsinghua University

Education

University of Illinois Urbana-Champaign

Peking University

Academic service

Honors