Hi, I’m Norman, Renhao Zhang (张仁浩), currently a Computer Science PhD candidate in the Autonomous Learning Laboratory at the University of Massachusetts Amherst, advised by Professor Bruno Castro da Silva.

I was fortunate to work with the Amazon Supply Chain Optimization Team, where I applied RL to inventory control problems, and with the AWS Quick team, where I worked on agentic planning methods for temporal reasoning.

I got my master’s degree in Electrical and Computer Engineering at Brown University, working on hierarchical RL with Prof. George Konidaris and computer graphics with Prof. Daniel Ritchie. Before that, I got my Bachelor’s degree in Electrical Information Engineering at Dalian University of Technology, advised by Prof. Xuanheng Li on applications of RL in wireless communication and Prof. Shenglan Liu on computer vision.

My research lies in reinforcement learning, bridging theory and practice. On the theoretical side, I study sample-efficient learning and continual reinforcement learning; on the practical side, I apply these ideas to robotics, LLMs, and AI safety. More details can be found in my research statement.

🔥 News

• 2026.10:  🎉 Our paper “Learning Generative Motion Manifolds for World Models” was accepted to the CoRL 2026 Workshop LEAP!
• 2026.10:   I was recognized as a ‘TOP REVIEWER’ for NeurIPS 2026.
• 2026.10:  🎉 Our paper “Learning What to Keep: Evidence-Gated Parameterized Skills for Frozen LLM Agents” was accepted to the NeurIPS 2026 Workshop TTCL!
• 2026.10:  🎉 Our paper “TRACE: Separating Action and Reasoning Teachers for Strategic SLM Training” was accepted to the NeurIPS 2026 Workshop SLMAgents!
• 2026.09:  🎉 Our paper “Uncertainty-Guided Reward Labeling for Reinforcement Learning under Limited Feedback” was accepted to the NeurIPS 2026!
• 2026.09:  🎉 Our paper “Latent Barrier Steering: Hierarchical Safety for Generative Planning” was accepted to the NeurIPS 2026!
• 2026.09:  🎉 Our paper “Data Selection for Reward Labeling in Limited-Feedback Reinforcement Learning” was accepted to the TMLR!
• 2025.09:  I’ll be a TA for COMPSCI 687: Reinforcement Learning in the Fall 2026 semester. Ask me anything in CSL E213 2-4 pm every Wednesday!
• 2026.06:  🎉 Our SURE paper was accepted to the ICML 2026 DEMO Workshop as a Spotlight!
• 2026.05:  Internship as an Applied Scientist Intern at the Amazon AWS Quick team. I’ll be in bay area from May to August, 2026.
• 2026.05: I’m now a PhD candidate.
• 2026.04:  🎉 Our PDP paper was accepted to the ICML 2026. Unfortunately, I won’t be able to be in Seoul to attend the conference in person.
• 2026.02:  🎉 Our PPROMPTMINERP paper was accepted to the CVPR 2026. I’ll be in Denver for it.
• 2025.10:  🎉 My internship paper was published at the Amazon Machine Learning Conference (AMLC 2025), a premier internal conference, for a highlight talk.

📝 Selected Publications

Latent Barrier Steering: Hierarchical Safety for Generative Planning

Renhao Zhang, Mingzhe Li, Bruno Castro da Silva

Paper (coming soon) | Code (coming soon)

NeurIPS 2026

Uncertainty-Guided Reward Labeling for Reinforcement Learning under Limited Feedback

Renhao Zhang, Shreyas Chaudhari, Bruno Castro da Silva

Paper(coming soon) | Code (coming soon)

NeurIPS 2026 & ICML 2026 DEMO Workshop (Spotlights)

From Noise to Control: Parameterized Diffusion Policies

Renhao Zhang, Haotian Fu, Mingxi Jia, George Konidaris, Yilun Du, Bruno Castro da Silva

Paper | Code | Project

ICML 2026

PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and Fuzz Optimization

Mingzhe Li, Renhao Zhang, Zheng Wen, Sheng Pan, Bruno Castro da Silva, Juan Zhai, Shiqing Ma

Paper | Code

CVPR 2026

Data Selection for Reward Labeling in Limited-Feedback Reinforcement Learning

Shreyas Chaudhari*, Renhao Zhang*, Philip S. Thomas, Bruno Castro da Silva

Paper | Code

TMLR

Learning to Edit Visual Programs with Self-Supervision

R. Kenny Jones, Renhao Zhang, Aditya Ganeshan, Daniel Ritchie

Paper | Code | Project

NeurIPS 2024

Model-based Reinforcement Learning for Parameterized Action Spaces

Renhao Zhang*, Haotian Fu*, Yilin Miao, George Konidaris

Paper | Code

ICML 2024

When DSA Meets SWIPT: A Joint Power Allocation and Time Splitting Scheme Based on Multi-Agent Deep Reinforcement Learning

Renhao Zhang, Xuanheng Li, Nan Zhao

Paper

IEEE Transactions on Vehicular Technology, 2023

🎖 Honors and Awards

• 2025.01  Paul Utgoff Memorial Scholarship, UMass Amherst.
• 2022.06  Outstanding Graduates, Dalian University of Technology.
• 2020.05  Second Prize, China Computer Design Competition.
• 2019.09  Scholarship for Academic Excellence.

📖 Educations

University of Massachusetts Amherst

Ph.D. in Computer Science, 2024.09 – NOW

Advisor: Bruno Castro da Silva

Harvard University

Visiting student in Computer Science, 2023.09 – 2023.12

Brown University

M.S. in Electrical & Computer Engineering, 2022.08 – 2024.05

Advisors: George Konidaris, Daniel Ritchie

Dalian University of Technology

B.S. in Electrical Information Engineering, 2018.09 – 2022.06

Advisors: Xuanheng Li, Shenglan Liu

💻 Internships

Amazon — AWS Quick team, Santa Clara, CA

Applied Scientist Intern, 2026.05 – 2026.08

Host: Arshit Gupta, Han He, Sailik Sengupta, James Gung

Project: Agentic planning with temporal reasoning.

Amazon — SCOT team, Bellevue, WA

Applied Scientist Intern, 2025.05 – 2025.08

Host: Mitchell Joblin, Alvaro Maggiar

Project: Learning Optimal Inventory Policies under Product Substitution using Hierarchical Reinforcement Learning.

Panasonic Software Development, Dalian, China

Algorithm Engineer Intern, 2021.06 – 2021.07

Project: Face recognition–based time and attendance system

🛎 Services

Technical Reviewer:

• NeurIPS: 2026 (top reviewer), 2025, 2024
• ICLR: 2027
• ICML: 2026, 2025
• AISTATS: 2025
• RLC: 2025
• AAAI: 2027

Teaching Assistant:

• COMPSCI 687: Reinforcement Learning, Fall 2026, UMass Amherst
• COMPSCI 389: Introduction to Machine Learning, Spring 2026, Fall 2025, UMass Amherst
• ENGN 2912B: Scientific Programming in C++, Fall 2024, Brown University
• CSCI 1951R: Introduction to Robotics, Fall 2024, Brown University
• Object Detection, Fall 2023, Dalian University of Technology