Zhenghao Peng

Hi there! I’m a Member of Technical Staff at Amazon FAR, working on robotics. I received my PhD in Computer Science from UCLA, advised by Prof. Bolei Zhou. Before UCLA, I earned my MPhil in the Multimedia Lab at the Chinese University of Hong Kong, and my Bachelor’s at Shanghai Jiao Tong University.

My research interests include Reinforcement Learning, Robotics, Multimodal LLM (VLA, VLM), and Human-in-the-loop Learning. I have 20+ top-tier conference papers, 5+ papers pioneering human-in-the-loop learning, 1800+ citations, and 9 first-/co-first-authored papers.

The singularity for AI/robotics hasn’t arrived. Plenty of unsolved problems still sit between today’s systems and general-purpose robots in the physical world. AI and robots will be one of the most transformative forces of our lifetimes. Whether that goes well for humans depends on the people building it now. Glad to be one of them.

Recent News

Apr 20, 2026	I joined Amazon FAR as a Member of Technical Staff. Excited to work here!
Jun 16, 2025	Two paper accepted to NeurIPS 2025.
Jun 16, 2025	I’ll be interning at the Autonomous Vehicles Research Group at NVIDIA this summer.
Jun 06, 2025	I received the Dissertation Year Award! Thanks, UCLA!
Feb 26, 2025	Papers on building RL env from video via 3D GS and improving VLM via MetaVQA were accepted to CVPR 2025.
Jan 27, 2025	Paper on applying human-in-the-loop learning on real robots was accepted to ICRA 2025.
Sep 25, 2024	Papers on shared autonomy (AI assists human) and diffusion on driving were accepted to NeurIPS 2024.
Jul 03, 2024	Paper on RL finetuning behavior model was accepted to ECCV 2024.
Jun 14, 2024	I am honored to receive the Amazon Fellowship. Many thanks to Amazon!
Sep 21, 2023	Human-in-the-loop learning method PVP was accepted to NeurIPS 2023 as Spotlight! ScenarioNet was accepted to NeurIPS 2023 Dataset Track!
Jun 19, 2023	I am starting an internship at Waymo! Great to be here at Bay Area!
Jan 28, 2023	TrafficGen on traffic scene generation was accepted to ICRA 2023. TS2C on learning super-teacher agent was accepted to ICLR 2023.
Sep 14, 2022	Policy Dissection was accepted to NeurIPS 2022!
Sep 10, 2022	I moved to UCLA. Go bruins!
Mar 28, 2022	MetaDrive white paper was accepted to TPAMI!
Jan 21, 2022	One paper on Human-AI Copilot (HACO) was accepted to ICLR 2022!
Sep 29, 2021	One paper on Multi-agent RL (CoPO) was accepted to NeurIPS 2021!
Sep 14, 2021	One paper on Safe RL (EGPO) was accepted to CoRL 2021!

Selected Projects

CVPR Highlight

Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning

Zhenghao Peng, Wenhao Ding, Yurong You, Yuxiao Chen, Wenjie Luo, Thomas Tian, Yulong Cao, Apoorva Sharma, Danfei Xu, Boris Ivanovic, Boyi Li, Bolei Zhou, Yan Wang, and Marco Pavone

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

PDF Website
NeurIPS Spotlight

Predictive Preference Learning from Human Interventions

Haoyuan Cai, Zhenghao Peng, and Bolei Zhou

In Advances in Neural Information Processing Systems, 2025

PDF Website
ICRA

Data-Efficient Learning from Human Interventions for Mobile Robots

Zhenghao Peng, Zhizheng Liu, and Bolei Zhou

In International Conference on Robotics and Automation, 2025

PDF Website
NeurIPS

Shared Autonomy with IDA: Interventional Diffusion Assistance

Brandon J. McMahan, Zhenghao Peng, Bolei Zhou, and Jonathan C. Kao

Advances in Neural Information Processing Systems, 2024

PDF
ECCV

Improving Agent Behaviors with RL Fine-tuning for Autonomous Driving

Zhenghao Peng, Wenjie Luo, Yiren Lu, Tianyi Shen, Cole Gulino, Ari Seff, and Justin Fu

In European Conference on Computer Vision, 2024

PDF
NeurIPS Spotlight

Learning from Active Human Involvement through Proxy Value Propagation

Zhenghao Peng, Wenjie Mo, Chenda Duan, Quanyi Li, and Bolei Zhou

In Advances in Neural Information Processing Systems, 2023

PDF Code Website
NeurIPS

ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling

Quanyi Li^*, Zhenghao Peng^*, Lan Feng^*, Zhizheng Liu, Chenda Duan, Wenjie Mo, and Bolei Zhou

In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2023

PDF Code Website
NeurIPS

Human-AI Shared Control via Policy Dissection

Quanyi Li, Zhenghao Peng, Haibin Wu, Lan Feng, and Bolei Zhou

In Advances in Neural Information Processing Systems, 2022

PDF Code Website
ICLR

Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization

Quanyi Li^*, Zhenghao Peng^*, and Bolei Zhou

In International Conference on Learning Representations, 2022

PDF Video Code Website
NeurIPS

Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization

Zhenghao Peng, Quanyi Li, Chunxiao Liu, and Bolei Zhou

In Advances in Neural Information Processing Systems, 2021

PDF Code Website
CoRL

Safe Driving via Expert Guided Policy Optimization

Zhenghao Peng^*, Quanyi Li^*, Chunxiao Liu, and Bolei Zhou

In 5th Annual Conference on Robot Learning , 2021

PDF Video Code Website
TPAMI

MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning

Quanyi Li^*, Zhenghao Peng^*, Lan Feng, Qihang Zhang, Zhenghai Xue, and Bolei Zhou

In , 2021

PDF Video Code Website

Fun facts:

Favourite robot: Tachikoma.
Pronunciation of my name.
I enjoy watching movie, cycling, and camping.