Mansi Sakarvadia

16 papers A* 1B 1C 1Journal 12Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
Empowering Scientific Workflows with Federated Agents.
CoRR
J. Gregory Pauloski, Yadu N. Babuji, Ryan Chard, Mansi Sakarvadia, Kyle Chard, Ian T. Foster
2025 A* conf
Mitigating Memorization in Language Models.
ICLR
Mansi Sakarvadia, Aswathy Ajith, Arham Mushtaq Khan, Nathaniel C. Hudson, Caleb Geniesse, Kyle Chard, Yaoqing Yang, Ian T. Foster, Michael W. Mahoney
2025 J jnl
SCOPE-MRI: Bankart Lesion Detection as a Case Study in Data Curation and Deep Learning for Challenging Diagnoses.
CoRR
Sahil Sethi, Sai Reddy, Mansi Sakarvadia, Jordan Serotte, Darlington Nwaudo, Nicholas Maassen, Lewis Shi
2025 J jnl
The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators.
CoRR
Mansi Sakarvadia, Kareem Hegazy, Amin Totounferoush, Kyle Chard, Yaoqing Yang, Ian T. Foster, Michael W. Mahoney
2025 J jnl
Topology-Aware Knowledge Propagation in Decentralized Learning.
CoRR
Mansi Sakarvadia, Nathaniel Hudson, Tian Li, Ian T. Foster, Kyle Chard
2024 J jnl
De Bello Homomorphico: Investigation of the extensibility of the OpenFHE library with basic mathematical functions by means of common approaches using the example of the CKKS cryptosystem.
Int. J. Inf. Sec.
Thomas Prantl, Lukas Horn, Simon Engel, Lukas Iffländer, Lukas Beierlieb, Christian Krupitzer, André Bauer, Mansi Sakarvadia, Ian T. Foster, Samuel Kounev
2024 J jnl
Mitigating Memorization In Language Models.
CoRR
Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Nathaniel Hudson, Caleb Geniesse, Kyle Chard, Yaoqing Yang, Ian T. Foster, Michael W. Mahoney
2024 J jnl
SoK: On Finding Common Ground in Loss Landscapes Using Deep Model Merging Techniques.
CoRR
Arham Khan, Todd Nief, Nathaniel Hudson, Mansi Sakarvadia, Daniel Grzenda, Aswathy Ajith, Jordan Pettyjohn, Kyle Chard, Ian T. Foster
2024 J jnl
Toward Non-Invasive Diagnosis of Bankart Lesions with Deep Learning.
CoRR
Sahil Sethi, Sai Reddy, Mansi Sakarvadia, Jordan Serotte, Darlington Nwaudo, Nicholas Maassen, Lewis Shi
2024 J jnl
Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning.
CoRR
Mansi Sakarvadia
2024 J jnl
Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision.
CoRR
Nathaniel Hudson, J. Gregory Pauloski, Matt Baughman, Alok Kamatar, Mansi Sakarvadia, Logan T. Ward, Ryan Chard, André Bauer, Maksim Levental, Wenyi Wang, Will Engler, Owen Price Skelly, Ben Blaiszik, Rick Stevens, Kyle Chard, Ian T. Foster
2023 J jnl
Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism.
CoRR
Mansi Sakarvadia, Arham Khan, Aswathy Ajith, Daniel Grzenda, Nathaniel Hudson, André Bauer, Kyle Chard, Ian T. Foster
2023 B conf
Lazy Python Dependency Management in Large-Scale Systems.
e-Science
Alok Kamatar, Mansi Sakarvadia, Valérie Hayot-Sasson, Kyle Chard, Ian T. Foster
2023 — conf
Memory Injections: Correcting Multi-Hop Reasoning Failures During Inference in Transformer-Based Language Models.
BlackboxNLP@EMNLP
Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Daniel Grzenda, Nathaniel Hudson, André Bauer, Kyle Chard, Ian T. Foster
2023 J jnl
Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models.
CoRR
Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Daniel Grzenda, Nathaniel Hudson, André Bauer, Kyle Chard, Ian T. Foster
2023 C conf
Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision.
BDCAT
Nathaniel Hudson, J. Gregory Pauloski, Matt Baughman, Alok Kamatar, Mansi Sakarvadia, Logan T. Ward, Ryan Chard, André Bauer, Maksim Levental, Wenyi Wang, Will Engler, Owen Price Skelly, Ben Blaiszik, Rick Stevens, Kyle Chard, Ian T. Foster