Hu Ding

WILD-Diffusion: A WDRO Inspired Training Method for Diffusion Models under Limited Data

Bridging Between Stable Rank and Data Selection: A Novel Sampling Method for Fast Training of Deep Neural Networks

CoBiSyn: A Bidirectional Search Framework for Chemical Synthesis Planning

Towards Adversarially Robust CLIP: A Hierarchical Model Fusion Method Using Optimal Transport

Relax and Merge: A Simple Yet Effective Framework for Solving Fair $k$-Means and $k$-sparse Wasserstein Barycenter Problems

Finding Wasserstein Ball Center: Efficient Algorithm and The Applications in Fairness

Bootstrap Your Uncertainty: Adaptive Robust Classification Driven by Optimal-Transport

Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness

Adaptive and Multi-scale Affinity Alignment for Hierarchical Contrastive Learning

To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation

An Effective Manifold-based Optimization Method for Distributionally Robust Classification

An Efficient Algorithm For Computing Optimal Wasserstein Ball Center