Publications
* indicates equal contribution
Evaluating and Monitoring Diffusion Models via Self-Supervised Principles | Project page
Xiao Li*, Yixuan Jia*, Zekai Zhang, Xiang Li, Lianghe Shi, Jinxin Zhou, Zhihui Zhu, Liyue Shen, Qing Qu. The 43rd International Conference on Machine Learning. ICML 2026.
Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
Xiao Li*, Zekai Zhang*, Xiang Li, Siyi Chen, Zhihui Zhu, Peng Wang, Qing Qu. The 39th Conference on Neural Information Processing Systems. NeurIPS 2025.
Understanding and Improving Transfer Learning of Deep Models via Neural Collapse
Xiao Li*, Sheng Liu*, Jinxin Zhou, Xinyu Lu, Carlos Fernandez-Granda, Zhihui Zhu, Qing Qu. Transactions on Machine Learning Research. TMLR 2024.
Generalization of Diffusion Models Arises with a Balanced Representation Space | Project page
Zekai Zhang*, Xiao Li*, Xiang Li, Lianghe Shi, Meng Wu, Molei Tao, Qing Qu. The 14th International Conference on Learning Representations. ICLR 2026.
Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
Peng Wang*, Xiao Li*, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, Qing Qu. Journal of Machine Learning Research. JMLR 2025.
Neural Collapse in Multi-label Learning with Pick-all-label Loss
Pengyu Li*, Xiao Li*, Yutong Wang, Qing Qu. The 41th International Conference on Machine Learning. ICML 2024.
Dynamic Low-rank Estimation for Transformer-based Language Models
Ting Hua*, Xiao Li*, Shangqian Gao, Yen-Chang Hsu, Yilin Shen, Hongxia Jin. The 2023 Conference on Empirical Methods in Natural Language Processing. EMNLP 2023 Findings.
On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features
Jinxin Zhou*, Xiao Li*, Tianyu Ding, Chong You, Qing Qu, Zhihui Zhu. The 39th International Conference on Machine Learning. ICML 2022.
Convolutional normalization: Improving deep convolutional network robustness and training
Sheng Liu*, Xiao Li*, Yuexiang Zhai, Chong You, Zhihui Zhu, Carlos Fernandez-Granda, Qing Qu. The 35th Conference on Neural Information Processing Systems. NeurIPS 2021.
ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing
Yixuan Jia, Siyi Chen, Yida Pan, Xiao Li, Lianghe Shi, Chanyong Jung, Haijie Yuan, Ismail Alkhouri, Yue Cynthia Wu, Saiprasad Ravishankar, et al. arXiv preprint arXiv:2605.14285. 2026.
MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
Xiang Li, Yixuan Jia, Xiao Li, Jeffrey A. Fessler, Rongrong Wang, Qing Qu. arXiv preprint arXiv:2603.22364. 2026.
Investigating the Catastrophic Forgetting in Multimodal Large Language Models
Yuexiang Zhai, Shengbang Tong, Xiao Li, Mu Cai, Qing Qu, Yong Jae Lee, Yi Ma. Conference on Parsimony and Learning. CPAL 2024.
Are All Losses Created Equal: A Neural Collapse Perspective
Jinxin Zhou, Chong You, Xiao Li, Kangning Liu, Sheng Liu, Qing Qu, Zhihui Zhu. The 35th Conference on Neural Information Processing Systems. NeurIPS 2022.
Deep-SMOLM: deep learning resolves the 3D orientations and 2D positions of overlapping single molecules with optimal nanoscale resolution
Tingting Wu, Peng Lu, Md Ashequr Rahman, Xiao Li, Matthew D Lew. Optics Express 30 (20), 36761-36773. Optics Express 2022.
A Geometric Analysis of Neural Collapse with Unconstrained Features
Zhihui Zhu*, Tianyu Ding*, Jinxin Zhou, Xiao Li, Chong You, Jeremias Sulam, Qing Qu. The 35th Conference on Neural Information Processing Systems. NeurIPS 2021.