Sara Babakniya — accepted AI-conference papers

2025

Escaping Collapse: The Strength of Weak Data for Large Language Model Training

Kareem Amin, Sara Babakniya, Alex Bie, Weiwei Kong, Umar Syed, Sergei Vassilvitskii

NeurIPS 2025poster

Synthetically-generated data plays an increasingly larger role in training large language models. However, while synthetic data has been found to be useful, studies have also shown that without proper curation it can cause LLM performance to plateau, or even "collapse", after many training iteration…

Cited by 0 Source ↗Scholar ↗

2023

A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks

Sara Babakniya, Zalan Fabian, Chaoyang He, Mahdi Soltanolkotabi, Salman Avestimehr

NeurIPS 2023poster

Deep learning models often suffer from forgetting previously learned information when trained on new data. This problem is exacerbated in federated learning (FL), where the data is distributed and can change independently for each user. Many solutions are proposed to resolve this catastrophic forget…

Cited by 37 Source ↗PDF ↗Scholar ↗