The Science of Physical AI Safety — CoRL 2026
Convening the AI-safety and robot-learning communities to establish a shared science — and a shared research agenda — for the interpretability, alignment, and control of robot foundation models.
CoRL 2026 · November 12 · Austin, Texas The Science of Physical AI Safety Convening the AI safety and robot learning communities to establish a shared science — and a shared research agenda — for the interpretability, alignment, and control of robot foundation models. $20,000 in travel, registration & accommodation grants Backing early-career researchers in physical AI safety. Apply now → Sponsored by o₁o₂ o₃aₜ OBSERVATION → ACTION TOKENS π(aₜ | o₁:ₜ) policy = RFM goal mis- generalization → physical harm interp. / alignment port here? Speakers Marco Pavone Stanford & NVIDIA…
saved by
related reading
- the-case-for-physical-ai-safety.pdfpaisi.ai
- blog | ICLR Blogposts 2026iclr-blogposts.github.io
- Fall 2026boazbk.github.io
- Statistical Physics for Ambitious Interpretability: A Workshop Retrospective — LessWronglesswrong.com
- Physical Intelligence (π)pi.website
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Seoul Alignment Workshop 2026: What We Learnedfar.ai
- Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
- 9th Workshop on Visualization for AI Explainabilityvisxai.io
- PhysWorldAI - Physical World AIphysworld-org.github.io
- What will be left for us to work on?normaltech.ai
- pdfopenreview.net