Andrew Wang

Google Scholar Twitter

Introduction

My name is Andrew Wang and I am an MSc student at the University of Toronto and the Vector Institute for Artificial Intelligence, supervised by Professor Sheila McIlraith. I am interested in understanding LLM agents in the hopes of making AI helpful and safe. I've worked on model-based RL, partially observable RL, and large language models.

Publications

Identifying the Risks of LM Agents with an LM-Emulated Sandbox (2023)

Yangjun Ruan*, Honghua Dong*, Andrew Wang, Silviu Pitis, Yongchao Zhou, Jimmy Ba, Yann Dubois, Chris J. Maddison, Tatsunori Hashimoto

Boosted Prompt Ensembles for Large Language Models (2023)

Silviu Pitis, Michael R Zhang, Andrew Wang, Jimmy Ba

Learning Belief Representations for Partially Observable Deep RL (ICML 2023)

Andrew Wang*, Andrew C Li*, Toryn Q Klassen, Rodrigo Toro Icarte, Sheila A McIlraith

Operator Splitting Value Iteration (NeurIPS 2022)

Amin Rakhsha, Andrew Wang, Mohammad Ghavamzadeh, Amir-massoud Farahmand

Selected Awards & Honors

• Vector Scholarship In Artificial Intelligence
• Department Of Computer Science Graduate Program Recruitment Award
• Natural Sciences And Engineering Research Council Of Canada - Canada Graduate Scholarship Masters