physical-intelligence

A 4B grounding foundation model for physical intelligence. Unifies detection, referring, pointing, OCR, GUI, and layout grounding, achieving SOTA overall across 34 benchmarks and improving robot generalization and data efficiency in controlled evaluations.

Open-source implementation of "RL Token: Bootstrapping Online RL with Vision-Language-Action Models"

[NeurIPS 2026] Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence

Benchmark robot policies and convert datasets. No framework lock-in.

Very minimal Implementation of Pi-Zero (https://www.pi.website/download/pi0.pdf). Vision Action Flow matching model

ROSClaw Swarm Coordination Runtime — Collaboration Grounding for Physical Intelligence. The Society Layer that elevates individual Agent intelligence into Collective Intelligence.

Reliable agent systems, now turning toward physical intelligence.

Public profile for Cornell Physical Intelligence (CUPI), a Cornell University student robotics organization.

Official website for Cornell Physical Intelligence (CUPI), a Cornell University student robotics organization.