Arjun Seshadri

Aug 16, 2024 | amazon.science | Ben Biggs |Arjun Seshadri |Yang Zou |Achin Jain

We present Diffusion Soup, a compartmentalization method for Text-to-Image Generation that averages the weights of diffusion models trained on sharded data. By construction, our approach enables training-free continual learning and unlearning with no additional memory or inference costs, since models corresponding to data shards can be added or removed by re-averaging.

Aug 22, 2023 | amazon.science | Austin Xu |Arjun Seshadri |Raghudeep Gadde |Raffay Hamid

Machine learning (ML) models thrive on data, but gathering and labeling training data can be a resource-intensive process. A common way to address this challenge is with synthetic data, but even synthetic data usually requires laborious hand annotation by human analysts. At this year’s Computer Vision and Pattern Recognition conference (CVPR), we presented a method called HandsOff that eliminates the need to hand-annotate synthetic image data.