Weak-to-Strong Generalization Even in Random Feature Networks, Provably
Zhiyuan Li, Toyota Technological Institute at Chicago
Mar 20, 2025
Location
Bendheim House 103
AI safety via Inference-time compute
Boaz Barak, Gordon McKay Professor of Computer Science, Harvard University
Mar 5, 2025
Location
Friend Center 006
Large Language Model Lecture Series: Can Machines Become Conscious?
Panel Discussion with Anil Ananthaswamy, David Chalmers, Michael Graziano
Mar 4, 2025
Towards Evaluating Trustworthiness of Natural Language Explanations
Balaraman Ravindran is the founding head of the Wadhwani School of Data Science and AI, the Robert Bosch Centre for Data Science & AI and the Centre for Responsible AI (CeRAI) at IIT Madras
Feb 24, 2025, 2:30 pm
Location
Bendheim House 103, 26 Prospect Avenue
Large AI Model Lecture Series: Just a Parrot? -- How Language Models Learn, Reason, and Self-Improve
Sanjeev Arora, Charles C. Fitzmorris Professor of Computer Science, Director of Princeton Language and Intelligence
Feb 18, 2025, 4:30 pm
Speaker
Getting Started with Large Language Models with Princeton Language and Intelligence
Jan 23, 2025, 2:00 pm
Speakers
- Simon Park
- Abhishek Panigrahi
Open-Source and Science in the Era of Foundation Models
Percy Liang, Stanford University and Center for Research Foundation Models
Dec 3, 2024, 1:00 pm
Successful evaluations for large language models
Jason Wei, Open AI
Nov 22, 2024, 12:00 pm
Location
Bendheim House 103
Scaling Paradigms for Large Language Models
Jason Wei, Open AI
Nov 21, 2024, 5:00 pm
Location
Friend Center 101
Lecture