 REFLECT: Rectified Flows for Efficient Brain Anomaly Correction TransportInternational Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2025 |
 Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion ModelsComputer Vision and Pattern Recognition (CVPR), 2025 |
 Generalization through variance: how noise shapes inductive biases in diffusion modelsInternational Conference on Learning Representations (ICLR), 2025 |
 EP-Diffuser: An Efficient Diffusion Model for Traffic Scene Generation and Prediction via Polynomial RepresentationsIEEE Robotics and Automation Letters (IEEE RA-L), 2025 |
Data Unlearning in Diffusion ModelsInternational Conference on Learning Representations (ICLR), 2025 |
