Udari Madhushani Sehwag (Preferred)
Udari Madhushani
Udari Madhushani Sehwag
Researcher, Scale AI
Postdoc, Computer Science Department, Stanford University
Joined
February 2020
Names
,
Emails
****@princeton.edu (Confirmed)
****@stanford.edu (Confirmed)
****@jpmorgan.com (Confirmed)
****@gmail.com (Confirmed)
****@scale.com (Confirmed)
Personal Links
Career & Education History
Researcher
Scale AI (scale.com)
2025 – Present
Postdoc
Computer Science Department, Stanford University (cs.stanford.edu)
2023 – Present
Researcher
J.P. Morgan Chase (jpmorgan.com)
2023 – 2025
PhD student
Princeton University (princeton.edu)
2017 – 2023
Advisors, Relations & Conflicts
Expertise
Scalable oversight
2023 – Present
Frontier safety
2023 – Present
Foundation model based agents
2022 – Present
Alignment
, collective alignment
2022 – Present
Evaluations and benchmarking foundation models
2022 – Present
Jailbreak
, safety and responsible generative AI
2022 – Present
Multi-agent learning
, multi-agent RL
2014 – 2022
Publications
Co-Authors
- Abhimanyu Dubey
- Aldana Belen Rodriguez
- Alec Koppel
- Alex Levinson
- Alex McAvoy
- Alex Pentland
- Amit Chakraborty
- Andrea Sarai Echeverria Toledo
- Antigoni Polychroniadou
- Arjun Karanam
- Bang An
- Bert Herring
- Bing Liu
- Biswadip Dey
- Bo Li
- Boyi Wei
- Brandon Handoko
- Bryan Zhu
- Chen Bo Calvin Zhang
- Christina Q Knight
- Dacheng Li
- Dalton towers
- Dan Borges
- Danqi Chen
- David Campbell