Research Artifacts

Noise Space Learning for VLA Adaptation

2026-10-09 · University of Technology Sydney / Microsoft Research / Nanjing University / Tsinghua University · Australia / ChinaSource

Preprint

MicrosoftPhysical Intelligence

University of Technology Sydney / Microsoft Research / Nanjing University / Tsinghua University

Robot learning / Foundation models

Dream to Remember: Continual Steering of Generalist Robot Policies with World Models

2026-10-09 · Bahey Tharwat / Iman Nematollahi · GermanySource

Preprint

Franka RoboticsPhysical Intelligence

Bahey Tharwat / Iman Nematollahi

Robot learning / Reinforcement learning

ARC: A Reasoning Recipe for Robot Foundation Models

2026-10-08 · University of Illinois Urbana-Champaign / Stanford University / NVIDIA / University of Sydney / Proception · United States / AustraliaSource

Preprint

NVIDIAProception AI

University of Illinois Urbana-Champaign / Stanford University / NVIDIA / University of Sydney / Proception

Robot learning / Manipulation

Physical Intelligence publishes pi0.7 steerable robotic foundation model

2026-04-16 · Physical Intelligence · United StatesSource

Model

Physical Intelligence

Foundation models / Robot learning

Physical Intelligence introduces π0.7 steerable generalist robot model

2026-04-16 · Physical Intelligence · United StatesSource

Model

Physical Intelligence

Foundation models / Robot learning

Physical Intelligence publishes RLT for efficient online reinforcement learning

2026-03-19 · Physical Intelligence · United StatesSource

Technical Report

Physical Intelligence

Reinforcement learning / Robot learning

Physical Intelligence introduces Multi-Scale Embodied Memory for long-horizon VLAs

2026-03-03 · Physical Intelligence · United StatesSource

Technical Report

Physical Intelligence

Foundation models / Robot learning

Physical Intelligence studies emergence of human-to-robot transfer in VLA models

2025-12-16 · Physical Intelligence · United StatesSource

Technical Report

Physical Intelligence

VLA Models / Robot learning

Physical Intelligence releases π*0.6 VLA reinforcement-learning method

2025-11-17 · Physical Intelligence · United StatesSource

Model

Physical Intelligence

Foundation models / Robot learning

Physical Intelligence publishes real-time action chunking for high-latency VLA control

2025-06-09 · Physical Intelligence · United StatesSource

Technical Report

Physical Intelligence

VLA Models / Robot learning

Physical Intelligence publishes VLA training method for faster training and stronger generalization

2025-05-28 · Physical Intelligence · United StatesSource

Technical Report

Physical Intelligence

VLA Models / Robot learning

Physical Intelligence publishes pi0.5 VLA for open-world generalization

2025-04-22 · Physical Intelligence · United StatesSource

Model

Physical Intelligence

Foundation models / Robot learning

Physical Intelligence open-sources pi0 weights and openpi repository

2025-02-04 · Physical Intelligence · United StatesSource

Repo

Physical Intelligence

Foundation models / VLA Models

Physical Intelligence releases FAST robot action tokenizer for efficient VLA training

2025-01-16 · Physical Intelligence · United StatesSource

Framework

Physical Intelligence

VLA Models / Robot learning

Physical Intelligence introduces pi0 general-purpose robot foundation model

2024-10-31 · Physical Intelligence · United StatesSource

Model

Physical Intelligence

Foundation models / Robot learning