Yi-Chen Lee — accepted AI-conference papers

2025

High-Order Flow Matching: Unified Framework and Sharp Statistical Rates

Maojiang Su, Jerry Yao-Chieh Hu, Yi-Chen Lee, Ning Zhu, Jui-Hui Chung, Shang Wu +3

NeurIPS 2025poster

Flow matching is an emerging generative modeling framework that learns continuous-time dynamics to map noise into data. To enhance expressiveness and sampling efficiency, recent works have explored incorporating high-order trajectory information. Despite the empirical success, a holistic theoretica…

Cited by 0 Source ↗Scholar ↗

2025

On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality

Jerry Yao-Chieh Hu, Weimin Wu, Yi-Chen Lee, Yu-Chao Huang, Minshuo Chen, Han Liu

ICLR 2025poster

We investigate the approximation and estimation rates of conditional diffusion transformers (DiTs) with classifier-free guidance. We present a comprehensive analysis for “in-context” conditional DiTs under various common assumptions: generic and strong Hölder, linear latent (subspace), and Lipschitz…

Cited by 10 Source ↗PDF ↗Scholar ↗