Alexander Wei

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 12

Top Topics

Distributed Representations

Connectionist Models

Hebbian Learning

Learning Process

Top Venues

Publications

Danny Halawi, Alexander Wei, Eric Wallace, Tony T. Wang, Nika Haghtalab, Jacob Steinhardt
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation. CoRR (2024)
Alexander Wei, Nika Haghtalab, Jacob Steinhardt
Jailbroken: How Does LLM Safety Training Fail? NeurIPS (2023)
Nicole Immorlica, Brendan Lucier, Vahideh H. Manshadi, Alexander Wei
Designing Approximately Optimal Search on Matching Platforms. Manag. Sci. 69 (8) (2023)
Alexander Wei, Nika Haghtalab, Jacob Steinhardt
Jailbroken: How Does LLM Safety Training Fail? CoRR (2023)
Meena Jagadeesan, Alexander Wei, Yixin Wang, Michael I. Jordan, Jacob Steinhardt
Learning Equilibria in Matching Markets with Bandit Feedback. J. ACM 70 (3) (2023)
Yaodong Yu, Zitong Yang, Alexander Wei, Yi Ma, Jacob Steinhardt
Predicting Out-of-Distribution Error with the Projection Norm. ICML (2022)
Alexander Wei, Wei Hu, Jacob Steinhardt
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize. ICML (2022)
Alexander Wei, Wei Hu, Jacob Steinhardt
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize. CoRR (2022)
Yaodong Yu, Alexander Wei, Sai Praneeth Karimireddy, Yi Ma, Michael I. Jordan
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels. CoRR (2022)
Yaodong Yu, Alexander Wei, Sai Praneeth Karimireddy, Yi Ma, Michael I. Jordan
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels. NeurIPS (2022)
Nika Haghtalab, Thodoris Lykouris, Sloan Nietert, Alexander Wei
Learning in Stackelberg Games with Non-myopic Agents. EC (2022)
Meena Jagadeesan, Alexander Wei, Yixin Wang, Michael I. Jordan, Jacob Steinhardt
Learning Equilibria in Matching Markets from Bandit Feedback. NeurIPS (2021)