SPIN @ CoRL 2026 — Structured Physical Intelligence

Overview

What does it take to achieve the physical intelligence of a five-year-old? Children learn to manipulate new objects and generalize skills from only a handful of interactions. Despite rapid progress in vision and language, today’s robots remain far less data-efficient and lack comparably rich training data.

Structured Physical Intelligence (SPIN) asks how physical priors and structured world representations can close this gap. Relevant approaches include Visual-Language-Action models (VLAs), world models, object-centric and compositional representations, affordances, and particle-based models. Robotics provides a direct test of whether these ideas support efficient generalization across locomotion, dexterous manipulation, hierarchical control, and few-shot learning.

The workshop brings researchers together to examine recent advances, current limitations, and open problems through contributed papers, invited talks, a panel discussion, and a live dexterous manipulation competition.

Research Questions

This half-day workshop is organized around five questions spanning structure, representation, learning, and evaluation for physical agents:

Q1 — What structure enables data-efficient physical intelligence? How can developmental and cognitive theories of human physical knowledge inspire structured representations in robotics, and which of those inductive biases actually pay off in practice?
Q2 — How should physical agents represent the world? Object-centric models, compositional structure, affordances and object interactions, particle motion representations, and multimodal grounding each propose a different answer. Which representations best support perception, prediction, and action?
Q3 — What should be built in, and what should emerge from scale? How should engineered structural priors interact with self-supervised learning, joint-embedding predictive architectures, VLAs, and world models as data and model size grow?
Q4 — How can structured models generalize and adapt? What enables parameter-efficient fine-tuning, prompting, adapters, multi-task and continual learning, and transfer across tasks, environments, and robot embodiments?
Q5 — How should progress be understood and evaluated? Which benchmarks and mechanistic interpretability methods reveal whether a model truly reasons about physical interactions, dynamics, and failure?

The Child–Robot Dexterity Challenge

How do today’s robots compare with a child on everyday manipulation tasks?

Side by side: a robot gripper and a child's hands assembling matching wooden parts — Same task, two kinds of physical intelligence. Image is placeholder material pending final permissions and credits.

A child can quickly pick up, turn, stack, and insert unfamiliar objects. This competition invites robotic systems to attempt the same kinds of tasks, creating a clear and constructive benchmark for current progress in dexterous manipulation. It is open to all researchers, students, and practitioners from academia and industry.

How it works

The competition will feature 10 dexterous manipulation tasks using familiar objects. Each task will be selected so that it can be completed by a child, providing an intuitive point of comparison for today’s robotic systems.

Key dates and participation details

Final task list: TBD. Examples may include picking up a small object, untwisting a bottle cap, inserting an object into a matching opening, building towers, and rotating a face of a Rubik’s cube.
Competition launch: TBD
Registration deadline: TBD

Hardware

We will provide hardware for participants to use. Platform details will be announced. Teams and participants are also encouraged to bring their own identical hardware, subject to approval.

Evaluation

On the day of the competition, every task will be evaluated against its own clearly defined success criterion. A panel of neutral judges will assess each attempt consistently, and each system’s performance will be compared task by task with the child’s performance on the same activities. The detailed judging procedure, number of attempts, and reporting format are TBD.

The goal is to produce a transparent, constructive view of current capabilities across a varied set of everyday tasks and to identify promising directions for future research.

Speakers

All four invited speakers are committed, and will also join the panel discussion.

Mike Rabbat

AMI Labs

Speaker & panelist

Talk title to be announced

Jeannette Bohg

Stanford University

Speaker & panelist

Talk title to be announced

Yunzhu Li

Columbia University

Speaker & panelist

Talk title to be announced

Georgia Chalvatzaki

TU Darmstadt

Speaker & panelist

Talk title to be announced

Schedule

Tentative morning half-day schedule, in person.

8:30	Welcome — opening remarks (10 min)
8:40	Keynote Talk 1 — 25 min + 5 min Q&A
9:10	Keynote Talk 2 — 25 min + 5 min Q&A
9:40	Poster session + coffee break — 40 min
10:20	Keynote Talk 3 — 25 min + 5 min Q&A
10:50	Keynote Talk 4 — 25 min + 5 min Q&A
11:20	The Child–Robot Dexterity Challenge — 40 min
12:00	Panel: What is Next in Structured Physical Intelligence Models? — 45 min, moderated by Amir Bar, with audience Q&A
12:45	Concluding remarks — 5 min
12:50	Adjourn

Call for Papers

We invite submissions on Structured Physical Intelligence and related approaches to representation, learning, reasoning, and control for physical agents. Topics include, but are not limited to:

Cognitive science foundations of physical intelligence
Visual-Language-Action models (VLAs) with structured representations
Structured world models for physical reasoning, prediction, and planning
Joint-embedding predictive architectures and self-supervised world models
Data and model scaling in robotic foundation models
Multimodal grounding for robotic foundation models
Object-centric models for robotics
Compositionality and reasoning techniques
Object interactions, affordances, and motion dynamics for robotics
Generative models for robotics (e.g., text-to-image/video/3D generation)
Efficient training and inference of VLAs and world models
Parameter-efficient fine-tuning, prompting, and adapters for robotic foundation models
Generalization of VLAs and world models to other domains
Multi-task and continual learning for VLAs and world models
Mechanistic interpretability of VLAs and world models

Submission Guidelines

Eligibility: Full papers (4–8 pages), accepted CoRL 2026 submissions, and extended abstracts (2 pages). We welcome submissions that are under review or were recently published.
Formatting: Authors should use the CoRL 2026 paper template.
Review and Presentation: Submitting authors will be asked to serve on the program committee. Accepted papers will be presented in person during the poster session.
Publication: This workshop is non-archival.
Best Paper Award: Strong submissions will be recommended during review, and a Best Paper will be selected by the workshop chairs.
Submission Link: To be announced.