Conference Agenda

Opening Remarks and Welcome Message

Can We Get the Scientific Benefits of AI Without the Risks of Autonomous Agents?

Navigating the Path to AGI, Safely and Responsibly

What is Understanding?

Developing a Gold-Standard AI Risk-Management Framework: A Research Agenda

Building Blocks for International Cooperation on Next-Generation AI

International AI Safety Assurance Agreements: Lessons From History, Feasibility Factors, and Hypotheses for the Future

Changing Machine Learning Methods to Operate in Safety-Critical Domains

AI Safety in Aviation and Avionics Applications

Safety of AI-Powered Robots: Dimensions, Challenges, and a Way Forward

Can LLMs Change Our Past?

Simulating Emergent LLM Social Behaviors in Multi-agent Systems

Engineering a World Designed for Safe Superintelligence

Outlook: AI and Media

Paths for Developing Ethical AI

Panel: Global Perspectives

Building Collective Intelligence With Artificial Intelligence

Game-Theoretic Guarantees for Human-Robot Systems

Jailbreaking LLM-Controlled Robots

Mitigating Catastrophic Misalignment Risk With AI Control

Real Ethics for Artificial Agents?

A Matter of Principle? AI Alignment as the Fair Treatment of Claims

Transparent Value Alignment: Foundations for Human-Centered Explainable AI in Alignment

AI and Economic Risk: Assessment and Mitigation

Red Lines for Existential Control

Hyperscaled: The Global Challenge of Sustainability in AI

Safety Cases: A Scalable Approach to Frontier AI Safety

An Insider’s Outlook on Global AI Coordination

Better Benchmarks: A Roadmap for High-Stakes Evaluation in the Age of Agentic AI

Getting AI Systems (Collectively) to Behave the Way We (Collectively) Want Them To

Axioms for AI Alignment From Human Feedback

Dynamic Preferences in AI Alignment: A Deliberative Democracy Lens

Engineering a Fair, Computing-mediated Society

Frontiers of Fairness: Socio-technical Challenges to Algorithmic Fairness and Justice

AI Fairness

Beyond Biases Towards Attention Ethics

AI and Elections: What We Learned in 2024

AI Manipulation and Freedom of Thought

AI Can Help Humans Find Common Ground in Democratic Deliberation

“I’m Afraid I Can’t Do That”: Unresolved Questions Around Agentic Refusal

AI Safety in Multi-agent LLM Systems

The Year(s) of the AI Agents: Opportunities and Challenges in Depth

Understanding the Implications of AI on Financial Markets

An Introduction to Mechanistic Interpretability

Establishing Effective Serious Incident Reporting Frameworks: Lessons From Safety-Critical Industries and the Novel Challenges of GPAI

Technical AI Governance: Navigating Transparency Challenges in Data and Evaluation

Foundation Model Transparency

Global Landscape of AI Governance

Panel: Strategic foresight for safe and ethical AI

IASEAI and the Future