Zheng, Chenyu

8 publications

ICML 2025 A Theory for Conditional Generative Modeling on Multiple Data Sources Rongzhen Wang, Yan Zhang, Chenyu Zheng, Chongxuan Li, Guoqiang Wu

ICLRW 2025 A Theory for Conditional Generative Modeling on Multiple Data Sources Rongzhen Wang, Yan Zhang, Chenyu Zheng, Chongxuan Li, Guoqiang Wu

NeurIPS 2025 Scaling Diffusion Transformers Efficiently via $\mu$P Chenyu Zheng, Xinyu Zhang, Rongzhen Wang, Wei Huang, Zhi Tian, Weilin Huang, Jun Zhu, Chongxuan Li

NeurIPS 2024 Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization Rongzhen Wang, Chenyu Zheng, Guoqiang Wu, Xu Min, Xiaolu Zhang, Jun Zhou, Chongxuan Li

NeurIPS 2024 On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability Chenyu Zheng, Wei Huang, Rongzhen Wang, Guoqiang Wu, Jun Zhu, Chongxuan Li

ICLR 2024 The Blessing of Randomness: SDE Beats ODE in General Diffusion-Based Image Editing Shen Nie, Hanzhong Allan Guo, Cheng Lu, Yuhao Zhou, Chenyu Zheng, Chongxuan Li

ICML 2023 Revisiting Discriminative vs. Generative Classifiers: Theory and Implications Chenyu Zheng, Guoqiang Wu, Fan Bao, Yue Cao, Chongxuan Li, Jun Zhu

NeurIPS 2023 Toward Understanding Generative Data Augmentation Chenyu Zheng, Guoqiang Wu, Chongxuan Li