About Me

• Hi! I am a second-year Ph.D. student at EECS, University of Michigan, advised by Prof. Qing Qu. Before joining U-M, I received my undergraduate and master’s degrees from the Wuhan University, majoring in software engineering and computer science, respectively, advised by Prof. Weiwei Liu.
• Generative AI and Machine Learning. My research focuses on developing diffusion models with strong generalization, particularly by enhancing learning from synthetic data and preventing model collapse. More recently, I focused on diffusion language models and on studying how to align the intrinsic structure of data with the generation paradigm, particularly the generation order.
• Machine Learning. I also investigated out-of-domain generalization and adversarial robustness in AI systems, with the goal of building models that remain reliable under distribution shifts and adversarial attacks.

Recent News

• 4/30/2026: One paper accepted by ICML 2026.
• 1/25/2026: One paper accepted by ICLR 2026.
• 9/26/2025: Passing the qualifying exam and become a PhD candidate.
• 9/18/2025: One paper accepted by NeurIPS 2025 as a spotlight paper.

Publications

A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
Lianghe Shi*, Meng Wu*, Huijie Zhang, Zekai Zhang, Molei Tao, Qing Qu.
ICML 2025 Workshop (Oral) and NeurIPS 2025 (Spotlight).
Website

Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
Xiao Li, Yixuan Jia, Zekai Zhang, Xiang Li, Lianghe Shi, Jinxin Zhou, Zhihui Zhu, Liyue Shen, Qing Qu.
ICML 2026.

Generalization of Diffusion Models Arises with a Balanced Representation Space
Zekai Zhang*, Xiao Li*, Xiang Li, Lianghe Shi, Meng Wu, Molei Tao, Qing Qu.
ICLR 2026 and DeepMath (Oral).

Adversarially robust unsupervised domain adaptation
Lianghe Shi*, Weiwei Liu. The journal of Artificial Intelligence. AIJ.

A Closer Look at Curriculum Adversarial Training: From an Online Perspective
Lianghe Shi*, Weiwei Liu. Proceedings of the 38th AAAI Conference on Artificial Intelligence. AAAI 2024.

Adversarial self-training improves robustness and generalization for gradual domain adaptation
Lianghe Shi*, Weiwei Liu. 37th Conference on Neural Information Processing Systems. NeurIPS 2023.

Teaching

• Graduate Student Instructor of EECS 501: Probability and Random Processes (Fall 2025)

Academic Services

• Conference Reviewer: NeurIPS, ICML, ICLR, AISTATS.