TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

GigaBrain 0.5M

The project describes a VLA policy trained with a world-model-conditioned RL framework, using world model rollouts (including human-in-the-loop data) to generate diverse training data for continual improvement.
Text Gen 4
Released: February 18, 2026

Overview

World-model-conditioned VLA trained via world-model-based reinforcement learning for robot manipulation and self-improvement.

About Physical Intelligence

Physical Intelligence is an AI robotics company developing foundation models and learning algorithms for robots and physically-actuated devices. The company created ฯ€0 (pi-zero), the first generalist robotic foundation model capable of controlling diverse robot platforms across multiple tasks including folding laundry, assembling boxes, bussing tables, and making coffee.

Industry: Artificial Intelligence
Company Size: 80
Location: San Francisco, CA, US
Website: pi.website
View Company Profile

Tools using GigaBrain 0.5M

No tools found for this model yet.

Last updated: April 6, 2026
0 AIs selected
Clear selection
#
Name
Task