🧑💻️ About Me
I was born and raised in Shenzhen, a beautiful seaside city in China, in 1998. Currently, I am a final-year PhD student in Computer Science at The Chinese University of Hong Kong, Shenzhen. Prior to pursuing my PhD, I earned my bachelor’s degree in Statistics from Sun Yat-sen University in Guangzhou, China, in 2020. My passions include mathematics, coding, and sports.
I have also had the privilege of interning at notable organizations such as SenseTime, Damo Academy, Alibaba, and Amazon, where I gained valuable experience and insights on Reinforcement Learning, Optimization and Generative AI.
💬 About My Research
Throughout my PhD studies, I have focused on tackling challenges in modern machine learning using insights from mathematical optimization.
One line of my research spans new techniques for combinatorial optimization, as demonstrated in Tang et al. UAI 2023, and distributed optimization, as seen in Tang et al. AAAI 2024.
Since 2022, I have also delved into the research of Generative AI, particularly Diffusion Generative Models. I have led several intriguing research projects in this area, including post-training and Reinforcement Learning with Human Feedback (RLHF) for diffusion models, as detailed in Tang et al. ICLR 2024 and Tang et al. 2024 Preprint. Additionally, I have explored advanced techniques from solving nonlinear equations to expedite the sampling of diffusion models, as presented in Tang et al. ICML 2024.
Recently, I have been shifting part of my research focus to the post-training of multi-modal large language models (LLMs) and their intersection with diffusion models.
🔥 News
- 2024.05: 🎉🎉 Hello there! I’ve just launched my homepage to share my journey in Machine Learning.
📝 Featured Publications
-
“Tuning-Free Alignment of Diffusion Models with Direct Noise Optimization”, Preprint (A short version in 2nd SPIGM workshop @ ICML 2024)
Zhiwei Tang, Jiangweizhi Peng, Jiasheng Tang, Mingyi Hong, Fan Wang, Tsung-Hui Chang
-
“Accelerating Parallel Sampling of Diffusion Models”, ICML 2024
Zhiwei Tang, Jiasheng Tang, Hao Luo, Fan Wang, Tsung-Hui Chang
-
“Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles”, ICLR 2024
Zhiwei Tang, Dmitry Rybin, Tsung-Hui Chang
-
“$z$-SignFedAvg: A Unified Stochastic Sign-based Compression for Federated Learning”, AAAI 2024
Zhiwei Tang, Yanmeng Wang, Tsung-Hui Chang
-
“Low-Rank Matrix Recovery With Unknown Correspondence”, UAI 2023
Zhiwei Tang, Tsung-Hui Chang, Xiaojing Ye, Hongyuan Zha
For my full publication list, please see my google scholar or my CV.
📖 Educations
- 2020.09 - Present, PhD in Computer Science, The Chinese University of Hong Kong, Shenzhen, China
- 2016.09 - 2020.07, BS in Statistics, Sun Yat-sen University, Guangzhou, China
🔍 Review Service
- NeurIPS 2021-2024
- ICLR 2024
- ICML 2022-2024
- ICASSP 2022-2023