Mansi Sakarvadia

Sakarvadia, Mansi, Aswathy Ajith, Arham Khan, Nathaniel Hudson, Caleb Geniesse, Kyle Chard, Yaoqing Yang, Ian Foster, and Michael W. Mahoney. "Mitigating memorization in language models." International Conference on Learning Representations (2025).

Sethi, Sahil, Sai Reddy, Mansi Sakarvadia, Jordan Serotte, Darlington Nwaudo, Nicholas Maassen, and Lewis Shi. "Toward Non-Invasive Diagnosis of Bankart Lesions with Deep Learning." SPIE Medical Imaging 2025: Computer-Aided Diagnosis (2025).

Khan, Arham, Todd Nief, Nathaniel Hudson, Mansi Sakarvadia, Daniel Grzenda, Aswathy Ajith, Jordan Pettyjohn, Kyle Chard, and Ian Foster. "Sok: On finding common ground in loss landscapes using deep model merging techniques." arXiv preprint arXiv:2410.12927 (2024).

Sakarvadia, Mansi. "Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning." University of Chicago Master's Thesis (2024).

Hudson, Nathaniel C., J. Gregory Pauloski, Matt Baughman, Alok Kamatar, Mansi Sakarvadia, Logan Ward, Ryan Chard et al. "Trillion parameter ai serving infrastructure for scientific discovery: A survey and vision." In Proceedings of the IEEE/ACM 10th International Conference on Big Data Computing, Applications and Technologies, pp. 1-10. 2023.

Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Daniel Grzenda, Nathaniel Hudson, Andre Bauer, Kyle Chard, Ian Foster. Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models. Blackbox NLP, Dec 2023.

Mansi Sakarvadia*, Arham Khan*, Aswathy Ajith, Daniel Grzenda, Nathaniel Hudson, André Bauer, Kyle Chard, Ian Foster. Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism. Attributing Model Behavior at Scale Workshop @ NEURIPS, Dec 2023. (* equal contribution)

Alok Kamatar, Mansi Sakarvadia, Valerie Hayot-Sasson, and Kyle Chard, Ian Foster. Lazy Python Dependency Management in Large-Scale Systems. In 2023 IEEE 19th International Conference on e-Science, Oct 2023.