10th Annual Center for Human-Compatible AI Workshop
News & Updates
About the Workshop
More information coming soon.
Call for Posters
The CHAI 2026 workshop will take place from June 4th–7th, 2026 at the Asilomar Hotel & Conference Grounds in Pacific Grove, CA. If you are interested in presenting a poster during the CHAI 2026 Workshop's poster session, we encourage you to submit your abstract below.
We are soliciting posters on AI safety, including but not limited to the following sub-areas:
- Provably beneficial AI
- LLM safety and guardrails
- Value alignment
- Interpretability
- Multi-agent systems and Cooperative AI
- Human-AI collaboration and assistance games
- Bounded rationality and rational agent architectures
- Characterizing the limitations and safety risks of modern AI systems
- AI governance
- AI ethics
- Structured safety cases
- Program synthesis
- Probabilistic programming
- Formal verification of AI systems
- Societal effects of AI
We also encourage submissions if you do not see your topic listed above and believe it is relevant to our workshop.
Acceptance of your poster submission guarantees one spot at the CHAI 2026 workshop, for the presenter you designate. Please ensure your designated presenter can attend before submitting.
The deadline for submitting is Wednesday, March 25th, 2026 at 11:59pm Pacific Standard Time. We'll notify you of our decision by Wednesday, April 8th, 2026.