Marco Pavone
Stanford & NVIDIA
Bio ↗
SPAIS 2026
CoRL Workshop
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.
Robotics is undergoing a paradigm shift — from modular perception–planning–control pipelines to general-purpose robot foundation models that act directly on the physical world.
Because RFMs inherit the same transformer/diffusion substrate that frontier AI-safety research has spent years dissecting, the field's tools for interpretability, alignment, and control may already transfer to robots Häon et al. 2025 Buurmeijer et al. 2026 Swann et al. 2026 Robey et al. 2026 Joseph et al. 2026 Jeong et al. 2026.
The safety case for Physical AI is acute Stocking & Häon 2026. Failure modes researchers study in LLMs — goal misgeneralization, specification gaming, jailbreaks, deceptive or unintended behavior Amodei et al. 2016 Hendrycks et al. 2021 Sharkey et al. 2025 — could become physical harms when the model controls a robot.
Yet the two communities best equipped to address this rarely meet: AI safety seldom touches physical hardware, and robot learning seldom engages frontier interpretability and alignment.
This workshop convenes them to establish the Science of Physical AI Safety — organized around three questions the field has not yet settled: what AI-safety tools transfer from LLMs, what guarantees carry over from classical robotics, and whether evaluating robot foundation models demands fundamentally new methods.
The event is built for active, collaborative work rather than passive listening: anchor talks and spotlights set the technical context, then breakout rooms drive toward grounded consensus, with speakers circulating as mentors. Every participant leaves a contributor to a single, collectively authored paper that names the field's open research problems and sets a shared research agenda.
The workshop is organized around three questions that the field has not yet answered. Each anchors talks, a breakout room, and a section of the final paper.
Do AI-safety techniques built for LLMs transfer to robot foundation models?
Does classical robotics safety transfer to robot foundation models?
Do RFMs require evaluation techniques that are meaningfully different from both LLMs and classical robotics?
Anchor speakers frame each of the core questions, putting concrete technical context on the table for the day's collaborative work.
Participants opt into a room aligned to one of the three key questions. Each group works to produce:
Breakout artifacts are aggregated into a single paper that names the field's open research problems and sets a shared research agenda. Every participant is a contributor.
Papers (up to 4 pages) on interpretability, alignment, control, and evaluation for robot foundation models. All accepted papers are presented as posters, with the top submissions invited to give lightning talks.
Visual media plus optional short analysis of an RFM safety failure beyond collision. Selected demos are spotlighted on the day.
We welcome and value diverse perspectives — and strongly encourage submissions across all career stages, genders, ethnicities, geographies, and institutional backgrounds. This is a real and meaningful commitment, not a formality: capturing the full range of viewpoints is this workshop's central purpose.
If you are a graduate student or early-career researcher working on physical AI safety, this grant is for you. This is one of the highest-stakes open problems in AI, and there is real room for your work to shape where it goes.
Robocurve is covering the cost toward getting there. They are funding ten grants of $2,000 each — $20,000 in total — for travel, registration and accommodation at SPAIS 2026 in Austin.
We are not looking for the longest publication list. We want people who have thought hard about why physical AI safety matters and who will make the breakout rooms better by being in them.
Grant selection runs entirely separately from paper review: applying, winning, or being turned down has no bearing on whether your paper is accepted, and vice versa. Grants are awarded and paid by the Physical AI Safety Institute (PAISI); the selection committee includes one Robocurve representative. We may pay your registration directly to the conference, with the balance transferred to you — awards may be taxable, and for recipients outside the US we're generally required to withhold a percentage of the cash portion. No visa support is included. Full terms and privacy details on the application form.
