Powei Chang — accepted AI-conference papers

2026

GeoRK2: Geometry-Guided Runge-Kutta Integration for Diffusion Transformer Acceleration

Chaoqun Sun, Zongjing Fu, Powei Chang, Jinpeng Zhang, Jianxiang Xiang, Yukang Gao +1

CVPR 2026

Diffusion transformer models deliver state-of-the-art image synthesis quality but suffer from prohibitively slow iterative sampling. Although reducing sampling steps accelerates inference, aggressive step schedules often distort intermediate features and degrade sample fidelity. We present GeoRK2, a

Cited by 0 Source ↗Scholar ↗

2026

SPICE: Submodular Penalized Information–Conflict Selection for Efficient Large Language Model Training

Powei Chang, Jinpeng Zhang, Bowen Chen, Chenyu Wang, Chenlu Guo, Yixing Zhang +6

ICLR 2026poster

Information-based data selection for instruction tuning is compelling: maximizing the log-determinant of the Fisher information yields a monotone submodular objective, enabling greedy algorithms to achieve a $(1-1/e)$ approximation under a cardinality budget. In practice, however, we identify allevi…

Cited by 0 Source ↗Scholar ↗