GitHub

This README is functionally complete as of 06/26/2025. So if you find something missing, please open an issue and we will take care of it as soon as possible.

🆕 [2025-6-26] Tutorial for Evaluation Updated

🆕 [2025-6-15] Model Checkpoints Uploaded. Tutorial for Training/Fine-tuning Updated

🆕 [2025-6-12] Made Public.

[Page] | [Paper]

This is the official implementation of From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models

Table of Contents

TODO

  • Add more complete documentation for training and evaluation. Currently, the code is all there, but the documentation is sparse.

  • Release all relevant model checkpoints on HF

Installation

Important

See the How to Set ENV Variables section for setting up the environment variables.

Install this codebase by first cloning it.

git clone --recurse-submodules https://github.com/ai4ce/INT-ACT.git
cd INT-ACT

Warning

It is imperative to use --recurse-submodules to clone this repository, as it contains several submodules that are required for the code to function properly (e.g., our fork of LeRobot, which we are working to get rid of at the moment so we can work with official LeRobot wheels).

Note

This codebase relies on uv to manage the virtual environments. It's not strictly required, but the authors can only provide support for this environment management system.

Now simply run

uv sync

Important

This only installed the dependency for training and inference server. Full-scale inference requires installing the inference client (simulator) dependencies.

Inference under different environments, such as Simpler, Simpler-ManiSkill3, Libero, or real world requires installing their own dependency in a separate environment.

Note

Server refers to the policy (

Read the original on github.com ↗