MS
Mansi Sakarvadia
cs.AIcs.LGcs.CLcs.CVcs.DCBankart LesionComputer-Aided DiagnosisDeep LearningGlenoid LabrumLabral Tear
On Valency
published · living versionsW_ngmr3326·v1 · currentpublished
Extremes on Rewind: Generating 1,000-Member Ensembles Initialized at a Final Condition
with Jerry Lin, Mu-Ting Chien, Elizabeth A. Barnes
1 version
Preprints & journals
18 papers in the corpus · 2023–2026Mitigating Memorization In Language Models2410.02159v3 · Mansi Sakarvadia, Aswathy Ajith, Arham Khan et al.2024 · 0 citationsarXiv
Extremes on Rewind: Generating 1,000-Member Ensembles Initialized at a Final Condition2608.19008v1 · Jerry Lin, Mu-Ting Chien, Mansi Sakarvadia et al.2026 · 0 citationsarXivon Valency
Interpreting Language Model Hidden States at Scale2608.10260v1 · Jordan Pettyjohn, Mansi Sakarvadia, Nathaniel Hudson et al.2026 · 0 citationsarXiv
AI-Assisted MRI Interpretation in Diagnosing Bankart and Reverse Bankart Lesions.42200663 · Sethi, Sahil, Reddy, Sai, Sakarvadia, Mansi et al.2026 · 0 citationsThe American journal of sports medicine. 2026;54(9):2244-2252
The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators2510.06646v2 · Mansi Sakarvadia, Kareem Hegazy, Amin Totounferoush et al.2025 · 0 citationsarXiv
Empowering Scientific Workflows with Federated Agents2505.05428v3 · Alok Kamatar, J. Gregory Pauloski, Yadu Babuji et al.2025 · 0 citationsarXiv
SCOPE-MRI: Bankart Lesion Detection as a Case Study in Data Curation and Deep Learning for Challenging Diagnoses.40395941 · Sethi, Sahil, Reddy, Sai, Sakarvadia, Mansi et al.2025 · 2 citationsArXiv. 2025
Toward Non-Invasive Diagnosis of Bankart Lesions with Deep Learning.39764408 · Sethi, Sahil, Reddy, Sai, Sakarvadia, Mansi et al.2025 · 0 citationsArXiv. 2024
SCOPE-MRI: Bankart Lesion Detection as a Case Study in Data Curation and Deep Learning for Challenging Diagnoses2504.20405v2 · Sahil Sethi, Sai Reddy, Mansi Sakarvadia et al.2025 · 2 citationsarXiv
Topology-Aware Knowledge Propagation in Decentralized Learning2505.11760v1 · Mansi Sakarvadia, Nathaniel Hudson, Tian Li et al.2025 · 0 citationsarXiv
Toward Non-Invasive Diagnosis of Bankart Lesions with Deep Learning2412.06717v1 · Sahil Sethi, Sai Reddy, Mansi Sakarvadia et al.2024 · 1 citationarXiv
Deep Model Merging: The Sister of Neural Network Interpretability -- A Survey2410.12927v2 · Arham Khan, Todd Nief, Nathaniel Hudson et al.2024 · 0 citationsarXiv
Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning2411.05037v1 · Mansi Sakarvadia2024 · 0 citationsarXiv
Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models2309.05605v3 · Mansi Sakarvadia, Aswathy Ajith, Arham Khan et al.2023 · 5 citationsarXiv
Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision2402.03480v1 · Nathaniel Hudson, J. Gregory Pauloski, Matt Baughman et al.2024 · 12 citationsarXiv
Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism2310.16270v1 · Mansi Sakarvadia, Arham Khan, Aswathy Ajith et al.2023 · 3 citationsarXiv
Career total: 18 works. 18 are in this corpus.Showing the 16 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.