eventConference
Stanford Causal Science Conference
Frontiers in AI Evaluation
Tim de Silva | AI Financial Advice: Supply, Demand, and Life Cycle Implications
SeminarOct 07, 202612:00 PM - 1:15 PM
October
07
2026
Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.
Sign Up For Latest News
Frontiers in AI Evaluation
This session covers the foundational knowledge of GPUs, including their architecture, functionality, and applications in computing. It provides an introduction to GPU computing through the lens of the Marlowe SuperPod and prepares learners for advanced topics such as GPU-accelerated data science and machine learning.
Location: CoDa W401
This session covers the foundational knowledge of GPUs, including their architecture, functionality, and applications in computing. It provides an introduction to GPU computing through the lens of the Marlowe SuperPod and prepares learners for advanced topics such as GPU-accelerated data science and machine learning.
Location: CoDa W401
For 9/23 and 10/7 only, sessions are at the David Packard Electrical Engineering Building, Room 101. Each session features a different Stanford speaker; talk titles are announced by the organizers.
For 9/23 and 10/7 only, sessions are at the David Packard Electrical Engineering Building, Room 101. Each session features a different Stanford speaker; talk titles are announced by the organizers.
The annual Causal Science Conference is a premier one-day, in-person event that brings together leading researchers and industry practitioners working in evaluation, experimentation, and causal inference. The conference showcases cutting-edge methodologies, emerging trends, and real-world applications that shape how data informs decision-making across domains.
This year’s conference will focus on AI evaluation, featuring diverse perspectives on how we evaluate AI systems—from methodological advances to applied case studies and normative inquiry.
General Admission: $375
Faculty/Staff: $85
Student/Postdoc: $45
Stanford Affiliates: Free
| Start Time | End Time | Session | Speaker(s) |
| 8:00 AM | 9:00 AM | Registration & Coffee | |
| 9:00 AM | 9:15 AM | Opening Remarks | Guido Imbens, Stanford Data Science Faculty Director, and Applied Econometrics Professor |
| 9:15 AM | 9:45 AM | AI's Models of the World, and Ours | Jon Kleinberg, Professor of Computer Science & Information Science, Cornell University |
| 9:45 AM | 10:15 AM | Why We Must Go Beyond Post-Training for Robust AI Alignment | Dylan Hadfield-Menell, Assistant Professor of Artificial Intelligence and Decision Making, MIT |
| 10:15 AM | 10:45 AM | Scalable Evaluation of Multimodal AI Systems for Creative Optimization | Bahareh Azarnoush, Director, Multimodal Generative AI & Causal Inference, Netflix |
| 10:45 AM | 11:15 AM | Break | |
| 11:15 AM | 11:45 AM | Evaluation Under Pressure: Lessons from Deploying Clinical AI at Scale | Zachary Lipton, Cofounder & CTO, Abridge | Associate Professor of Machine Learning, Carnegie Mellon University |
| 11:45 AM | 12:15 PM | AI and Human Learning | Emma Brunskill, Associate Professor of Computer Science, Stanford University |
| 12:15 PM | 1:45 PM | Lunch & Poster Session | |
| 1:45 PM | 2:15 PM | The Benchmark Problem | Benjamin Recht, Professor of Electrical Engineering & Computer Sciences, UC Berkeley |
| 2:15 PM | 2:45 PM | Benchmarking to Advance the AI Frontier | Ofir Press, Research Scientist, Meta FAIR |
| 2:45 PM | 3:15 PM | Keeping up with AI capabilities | David Rein, Member of Technical Staff, METR |
| 3:15 PM | 3:45 PM | Break | |
| 3:45 PM | 4:15 PM | Towards Self-Driving Software Reliability | Anish Agarwal, CEO, Traversal | Assistant Professor, Columbia University |
| 4:15 PM | 4:45 PM | Optimize Your Agent's GPA with Coding Agents | Anupam Datta, Principal Research Scientist, Snowflake |
| 4:45 PM | 6:00 PM | Reception & Poster Session |
