AA228/CS238 Decision Making Under Uncertainty Lecture on Policy Gradient Estimation
Lecture, Stanford University, Stanford, CA
I gave a lecture on policy gradient estimation! You can watch my talk here.
ASTPrompter: Weakly Supervised Automated Language Model Red-Teaming to Identify Likely Toxic Prompts
Invited talk, Leibniz Center For European Economic Research, Remote
I was invited to give a talk on ASTPrompter at the Leibniz Center For European Economic Research workshop on Designing Procedures for Red Teaming Generative AI Models.
Developing an LLM-Based Cockpit Assistant
Invited talk, NASA Human Systems Integration, Mountain View, CA
I was invited to give a talk on my work with SISL + Airbus on building an LLM-based cockpit assistant and a framework to evaluate it.
Effective Social Chatbot Strategies for Increasing User Initiative
Conference presentation, SIGDIAL, Remote
I presented my work on strategies for increasing user intiative in human-bot dialogues. You can watch my talk here.