Event Details

About the Meeting

Our annual meeting provides a unique opportunity to engage with cutting-edge research, explore emerging challenges in AI safety, and connect with fellow researchers and practitioners committed to developing safe and trustworthy AI systems. The event will feature presentations from faculty, postdocs, and graduate students, showcasing the breadth and depth of research within our center.

We look forward to welcoming our corporate affiliates, academic collaborators, and the broader AI safety community for this important gathering.

Photos from our 2024 Annual Meeting

Agenda (Tentative)

For the most up-to-date agenda, please visit our live agenda spreadsheet.

Poster Presentations

Student poster presentations showcase cutting-edge research from our graduate students, postdoctoral scholars, and staff.

• The Measurement Imbalance in Agentic AI Evaluation Undermines Industry Productivity Claims (Allie Griffith)
• Robust AI for the Lunar Autonomy Challenge (Adam Dai)
• Distributional Robustness of Learned Features for 3D Map Localization (Daniel Neamati)
• From Principles to Practice: The ARGO Framework for Responsible AI Governance (Gabriela Aránguiz Dias)
• LuPNT: An Open-Source Simulator for Lunar Communications, Positioning, Navigation, and Timing (Guillem Vila)
• Efficient Failure Discovery for Commercial AV Systems (Hailey Warner)
• Safe and Performant Deployment of Autonomous Systems via Model Predictive Control and Hamilton-Jacobi Reachability Analysis (Hao Wang)
• ASTRA-RL: Adaptive Stress Testing for Robust AI with Reinforcement Learning (Houjun Liu)
• Incorporating Diffusion-Based Falsification into the POMDPs.jl Ecosystem (Jun Wang)
• Importance Sampling-Guided Meta-Training for Intelligent Agents in Highly Interactive Environments (Mansur Arief)
• Moving Beyond Medical Exam Questions: A Clinician-Annotated Dataset of Real-World Tasks and Ambiguity in Mental Healthcare (Max Lamparth)
• Verifying Nonlinear Neural Feedback Systems (Samuel Akinwande)
• Limit Theorems for Stochastic Gradient Descent with Infinite Variance (Wenhao Yang)

Registration

Join us on Monday, September 22, 2025 at Paul Brest Hall.
RSVP is required for this event.

Parking Information

Parking is available at Wilbur Field Garage (560 Wilbur Way, Stanford, CA 94305), but you have to register your car at stanford.aimsparking.com.

Purchase Event Parking → Daily Permits→ AI Safety annual meeting. Use the provided voucher code.

Upon arrival, use EA, ES, and SO spaces at lower levels 3 and 4. Spaces will not be reserved.

Highlights from Previous Events

Ways to Engage with the Center