WALL-OSS#

← Tutorial Library · policies and Models

This section introduces the general functions of LeRobot. Please configure the example according to the target robot, data set and operating environment; before using it with AlohaMini 2 / 2 Pro, you need to confirm the hardware and interface compatibility.

WALL-OSS is an open-source foundation model for embodied intelligence, proposed by the XSquare Robot team in 2025. The LeRobot implementation is adapted from their open-source WallX repository.

X Square Robot’s WALL-OSS is now integrated into Hugging Face’s LeRobot ecosystem. This is an exciting collaborative project between the LeRobot and X Square Robot teams. You can now post-train, evaluate, and deploy WALL-OSS directly through LeRobot. With this, we’re aiming to make it easier for the open-source robotics community to customize and deploy WALL-OSS foundation models. Read and explore WALL-OSS paper and code.

Model Overview#

The WALL-OSS team is building the embodied foundation model to capture and compress the world’s most valuable data: the continuous, high-fidelity stream of physical interaction. By creating a direct feedback loop between the model’s decisions and the body’s lived experience, the emergence of a truly generalizable intelligence is enabled—one that understands not just how the world works, but how to act effectively within it.

An overview of WALL-OSS

Technically, WALL-OSS introduces a tightly coupled multimodal architecture (tightly-coupled MoE structure) that integrates both discrete and continuous action modeling strategies. Through a two-stage training pipeline (Inspiration → Integration), the model gradually unifies semantic reasoning and high-frequency action generation. Its core innovations include:

  • Embodied perception–enhanced multimodal pretraining: Large-scale training on unified vision–language–action data to strengthen spatial, causal, and manipulation understanding.

  • Unified Cross-Level Chain-of-Thought (Uni-CoT): A single differentiable framework that unifies high-level instruction reasoning, sub-task decomposition, and fine-grained action synthesis, forming a continuous chain from “understanding” to “execution.”

  • Mixture-of-Experts (MoE) action heads: Dynamically activating experts depending on the task phase and modeling actions in discrete or continuous space to maintain stable VLM priors.

  • Two-stage training paradigm:

    • Inspiration stage: Injecting discrete action priors to strengthen spatial understanding and semantic-action alignment.

    • Integration stage: Using flow matching to achieve high-frequency continuous control.

Installation Requirements#

  1. Install LeRobot by following our Installation Guide.

  2. Install WallX dependencies by running:

    pip install -e ".[wallx]"

Usage#

To use WallX in LeRobot, specify the policy type as:

policy.type=wall_x

Training#

For training WallX, you can use the standard LeRobot training script with the appropriate configuration:

lerobot-train \
    --dataset.repo_id=your_dataset \
    --policy.type=wall_x \
    --output_dir=./outputs/wallx_training \
    --job_name=wallx_training \
    --policy.repo_id=your_repo_id \
    --policy.pretrained_name_or_path=x-square-robot/wall-oss-flow \
    --policy.prediction_mode=diffusion \
    --policy.attn_implementation=eager \
    --steps=3000 \
    --policy.device=cuda \
    --batch_size=32

Training Arguments#

Argument

Description

--dataset.repo_id

The Hugging Face Hub repository ID for your training dataset (e.g., lerobot/aloha_sim_insertion_human)

--policy.type

Specifies using the WallX policy architecture

--output_dir

Local directory where training checkpoints and logs will be saved

--job_name

A name identifier for this training run (used in logging/tracking)

--policy.repo_id

Your Hugging Face Hub repo ID where the trained model will be pushed

--policy.pretrained_path

Path to pretrained WallX weights to initialize from (the official WALL-OSS checkpoint)

--policy.prediction_mode

The action prediction strategy: diffusion or fast - diffusion uses iterative denoising for action generation, fast uses next token prediction instead

--policy.attn_implementation

Attention implementation backend - eager uses standard PyTorch attention (alternatives include flash_attention_2 or sdpa)

--steps

Total number of training steps to run

--policy.device

Device to train on (cuda for GPU, cpu for CPU)

--batch_size

Number of samples per training batch

License#

This model follows the Apache 2.0 License, consistent with the original WallX repository.