Scholar
Vinith M. Suriyakumar
Google Scholar ID: mP-esmMAAAAJ
Massachusetts Institute of Technology
Citations & Impact
Citations
432
H-index
7
i10-index
7
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Received multiple awards at NeurIPS, ICLR, ICML, and FAccT: ICML 2022 Spotlight, ICML 2023 Oral, ICLR 2024 Oral, FAccT 2024 Best Paper Award, NeurIPS 2025 Spotlight. Additionally, gave invited talks on open-weight model safety and unlearning at the MITAI Conference and the Bridgewater AIA Distinguished Speaker Series.
Research Experience
- Conducting research at MIT EECS, LIDS, IMES, and Bridgewater Associates. The main focus is on uncovering risks of open-weight models, applying interpretability to understand these risks, and building safeguards to address these risks.
Education
- Fifth year PhD student at MIT EECS, advised by Dr. Ashia Wilson and Dr. Marzyeh Ghassemi. Also frequently collaborates with Dr. Dylan Hadfield-Menell. Supported through a fellowship from Bridgewater Associates and AIA Lab led by Dr. Jas Sekhon where I also conduct research part-time.
Background
- Broadly, I’m interested in the privacy, security, and safety of machine learning. Throughout my Masters and PhD, I’ve worked on many topics in these areas including differential privacy, auditing, algorithmic fairness, and unlearning. These days, the goal of my research is to prevent the misuse of foundation models, especially when it comes to open-sourcing these models.
Miscellany
- Email is the best way to reach me. Feel free to send me a message if anything interests you!
Co-authors