2 papers
cs.CV2024
Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements
Shijie Zhou, Huaisheng Zhu, Rohan Sharma +4
Diffusion models have emerged as a powerful foundation model for visual generations. With an appropriate sampling process, it can effectively serve as a generative prior for solvin…
cs.LG2024
Discriminative Adversarial Unlearning
Rohan Sharma, Shijie Zhou, Kaiyi Ji +1
We introduce a novel machine unlearning framework founded upon the established principles of the min-max optimization paradigm. We capitalize on the capabilities of strong Membersh…