Scholar
Alexander Wei
Google Scholar ID: d5wGxRsAAAAJ
OpenAI
Citations & Impact
Citations
3,777
H-index
14
i10-index
15
Publications
18
Co-authors
20
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publications:
- - Jailbroken: How Does LLM Safety Training Fail?, NeurIPS 2023
- - Learning Equilibria in Matching Markets from Bandit Feedback, Journal of the ACM, 2023
- - Human-Level Play in the Game of Diplomacy by Combining Language Models with Strategic Reasoning, Science, 2022
- - Designing Approximately Optimal Search on Matching Platforms, Management Science, 2022
- - Optimal Las Vegas Approximate Near Neighbors in ℓ_p, ACM Transactions on Algorithms, 2022
- Awards:
- - SODA Best Student Paper award
- - INFORMS Auctions & Market Design Rothkopf Prize
- - Meta Research PhD Fellowship (2022-2023)
- - NSF Graduate Research Fellowship (2020-2023)
- - CRA Outstanding Undergraduate Researcher (2020)
- - Gold Medal, International Olympiad in Informatics (2015)
Research Experience
- Research scientist at OpenAI, was part of the FAIR team that developed CICERO.
Education
- Received a Ph.D. in Computer Science from UC Berkeley in 2023, advised by Nika Haghtalab, Michael I. Jordan, and Jacob Steinhardt. Completed A.B. and S.M. at Harvard in 2020, advised by Jelani Nelson and Scott Kominers.
Background
- Research interests include large language models and reasoning. Previously worked at the intersection of machine learning, game theory, and algorithms. Part of the team at FAIR that built CICERO, the first human-level AI for the game of Diplomacy.
Miscellany
- Contact information requires JavaScript to display.
