Jiangweizhi Peng

PhD student, ISyE, University of Minnesota - Twin Cities

Joined

February 2024

Names

Jiangweizhi Peng (Preferred)

Emails

****@umn.edu (Confirmed)

Personal Links

Career & Education History

PhD student

ISyE, University of Minnesota - Twin Cities (umn.edu)

2023 – Present

Advisors, Relations & Conflicts

PhD Advisor

2023 – Present

Expertise

Reinforcement Learning

2025 – Present

LLM Agents

2025 – Present

Diffusion Models

2023 – Present

Publications

Safeguarding Text-to-Image Generation via Inference-Time Prompt-Noise Optimization
Jiangweizhi Peng, Zhiwei Tang, Gaowen Liu, Charles Fleming, Mingyi Hong
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
RT2I-Bench: Evaluating Robustness of Text-to-Image Systems Against Adversarial Attacks
Athanasios Glentis, Ioannis Tsaknakis, Jiangweizhi Peng, Xun Xian, Yihua Zhang, Gaowen Liu, Charles Fleming, Mingyi Hong
- Accepted by TMLR
- Readers: Everyone
Distributed Hierarchical Decomposition Framework for Multimodal Timeseries Prediction
Wei Ye, Prashant Khanduri, Jiangweizhi Peng, Feng Tian, Jun Gao, Jie Ding, Zhi-Li Zhang, Mingyi Hong
- Accepted by TMLR
- Readers: Everyone
Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
Zhiwei Tang, Jiangweizhi Peng, Jiasheng Tang, Mingyi Hong, Fan Wang, Tsung-Hui Chang
- ICML 2025 poster
- Readers: Everyone
Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
Zhiwei Tang, Jiangweizhi Peng, Jiasheng Tang, Mingyi Hong, Fan Wang, Tsung-Hui Chang
- Submitted to ICLR 2025
- Readers: Everyone
Tuning-Free Alignment of Diffusion Models with Direct Noise Optimization
Zhiwei Tang, Jiangweizhi Peng, Jiasheng Tang, Mingyi Hong, Fan Wang, Tsung-Hui Chang
- 2nd SPIGM @ ICML Poster
- Readers: Everyone

Co-Authors