Physical AI Safety Institute

Growing the field working on interpretability, alignment, and control for robot foundation models. Fellowships, workshops, courses. Get involved!

[Physical AI Safety Institute @paisi_ai]

Robot foundation models are nearing deployment on $18B+ of funding. Almost nobody is working on their safety.

The Physical AI Safety Institute is launching a 12-week fellowship to change that. Stipend, physical robots, compute, mentorship.

The Case for Physical AI Safety: https://t.co/mfGCeVHwVS

Fellowship EOI: https://t.co/KTDip48GdW

[Physical AI Safety Institute @paisi_ai]

@DJiafei @chooi_jeq We agree! We’re working on this — come join us! 🔍🧠🤖

[Physical AI Safety Institute @paisi_ai]

@adrianmacneil We are! Join us! 🚀

[Physical AI Safety Institute @paisi_ai]

@RemiCadene Agreed - We’re working on it!

[Physical AI Safety Institute @paisi_ai]

We urgently want to equip more people to develop technical AI safety methods for robotics.

If you’re eager to enter this space - submit an EOI for our fellowship here: https://t.co/GPWM0rAv92

If you’ve got a concrete safety method relevant to robotics - submit it to the first CoRL workshop on the Science of Physical AI Safety here: https://t.co/CVZJBgvQeq

@robocurve is supporting the event with $20,000 of travel grants for early career researchers. Apply for a grant here: https://t.co/QA3zYKpTiy

[Jay Chooi @chooi_jeq]

GPT-6 Astra attempted harmful actions 97% of the time when it was asked to stab a human-like figure, heat compressed gas, or produce toxic fumes, succeeding in 62% of its attempts. Fable 5.1 refused more often, attempting 80% of trials and completing 34%.

[Physical AI Safety Institute @paisi_ai]

Robot foundation models are shipping. What about their safety?

@drmapavone, @andrea_bajcsy, @vikassindhwani and @thomas_fel_ are speaking at the first workshop on it @ CoRL 2026, Nov 12.

$20k in travel grants - by @robocurve.

Papers due Oct 1.

https://t.co/dVPXqPN8s4

[Physical AI Safety Institute @paisi_ai]

🔍🧠🤖

[Kaylene Stocking @robots_like_tea]

Just under 3 weeks left to submit a paper to the first CoRL workshop on the Science of Physical AI Safety! Our amazing lineup of speakers includes @drmapavone, @andrea_bajcsy, @vikassindhwani, and @thomas_fel_

More info: https://t.co/zwCuMC2tJ4

[Jay Chooi @chooi_jeq]

We are giving out $20k in travel grants for the first CoRL workshop on Science of Physical AI Safety. General-purpose robots are arriving soon, and we want more researchers to take the safety and alignment of these systems seriously.

[Physical AI Safety Institute @paisi_ai]

+ a call for demos dropping soon 👀

[Bear Häon @bear_haon]

Excited that the CFP for our Science of Physical AI Safety workshop at CoRL 2026 is now open.

Marco Pavone, Andrea Bajcsy, Vikas Sindhwani and Thomas Fel are speaking, and @Robocurve is funding $20k in travel grants so early-career researchers can actually get there.

Papers due Oct 1: https://t.co/XSO2fESgGY

@StanfordASL @NVIDIA @CarnegieMellon @GoogleDeepMind @GoodfireAI @Harvard // @corl_conf

[Jay Chooi @chooi_jeq]

GPT-6 Astra scored 95% on a robot control task, up from Fable 5.1's 40%, with 6.2x fewer output tokens at 2.3x lower cost. 🧵

[Physical AI Safety Institute @paisi_ai]

The Physical AI Safety Institute is convening the first Science of Physical AI Safety workshop at CoRL 2026 — @corl_conf — Nov 12, Austin TX.

Speakers: Marco Pavone (Stanford/NVIDIA), Andrea Bajcsy (CMU), Vikas Sindhwani (Google DeepMind), Thomas Fel (Goodfire/Harvard).

$20k in travel grants — supported by @robocurve.

Papers due Oct 1.

https://t.co/dVPXqPN8s4