Sign in

Mansi Sakarvadia

@mansisakarvadia.bsky.social
16 followers 8 following 14 posts

UChicago CS PhD Student | Department of Energy Computational Science Graduate Fellow | mansisak.com

PostsRepliesMedia
Mansi Sakarvadia @mansisakarvadia.bsky.social · 20/06/2025
🤝 New advances in decentralized learning! "Topology-Aware Knowledge Propagation in Decentralized Learning" proposes a novel way to improve how information flows in distributed machine learning systems. Let’s break it down! 🧵 (1/6) (arxiv.org/abs/2505.11760)
120
Reposted by Mansi Sakarvadia
Globus Labs @globuslabs.bsky.social · 29/04/2025
@mansisakarvadia.bsky.social, Aswathy (PhD students), and @nathaniel-hudson.bsky.social (postdoc) presented their work on identifying and ablating memorization in #LLMs at the 2024 MSLD workshop! 🎉 Their research is also accepted to ICLR 2025 — check it out: mansisak.com/memorization/
Mansi, Aswathy, and Nathaniel are presenting their poster.Mansi presentingMansi, Aswathy, and Nathaniel are standing infront of a nice building
032
Mansi Sakarvadia @mansisakarvadia.bsky.social · 04/03/2025
1/🧵ICLR 2025 Spotlight Research on LM & Memorization! Language models (LMs) often "memorize" data, leading to privacy risks. This paper explores ways to reduce that! Paper: arxiv.org/pdf/2410.02159 Code: github.com/msakarvadia/... Blog: mansisak.com/memorization/
172
Reposted by Mansi Sakarvadia
Globus Labs @globuslabs.bsky.social · 12/02/2025
Congratulations to @mansisakarvadia.bsky.social and team on their "Mitigating Memorization in Language Models" paper being selected as a Spotlight paper at ICLR '25! Check out the pre-print here: arxiv.org/abs/2410.02159
arxiv.org
Mitigating Memorization In Language Models
Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that data. This ability to...
033
Reposted by Mansi Sakarvadia
Globus Labs @globuslabs.bsky.social · 28/01/2025
How can we stop LLMs from memorizing information? @mansisakarvadia.bsky.social's paper, which develops new methods for unlearning memorized information and introduces a suite of small LMs for testing these methods, was just accepted to ICLR '25! arxiv.org/pdf/2410.02159
arxiv.org
121
Mansi Sakarvadia @mansisakarvadia.bsky.social · 05/01/2025
Reflecting on my 2024 PhD journey: passed my qualifying exam, spent the summer at Berkeley, mentored undergrad students, and tackled the fast pace of AI/ML research. It’s been a year of milestones and growth! Read more here: mansisak.com/blog/2025/ye... #PhDJourney #AIResearch
mansisak.com
A Year In Review: C.S. PhD Student Edition | Mansi Sakarvadia
A recap of my academic journey in 2024.
092