From 603d44434f432c79765c6e18c290fccac1bd7b3e Mon Sep 17 00:00:00 2001 From: Tong Wu <54630004+wut19@users.noreply.github.com> Date: Tue, 6 Jan 2026 22:13:35 +0800 Subject: [PATCH] fix a bug for kwargs in wallx (#2714) * support wallx * fix bugs in flow * incorporate wallx model into lerobot * update the policy methods * reduce to least config and params & pass lerobot basic test * fixed dtype bugs * add wallx dependencies * update * remove flash-attn requirement && fix bug in inference and fast mode * fix bug for inference * add some small modifications * fix pre-commit errors * remove lerobot[wallx] * fix ci * fix precommit issues * fix: exclude wallx extra properly in CI workflows * fix: add uv conflicts for wallx transformers version * fix: peft test import * pre-commit * only export WallXConfig from wall_x package to avoid peft import in CI * remove torch dep * precommit * add import * update doc files * fix minor errors * fix a bug for kwargs * fix precommit issue --------- Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com> Co-authored-by: vincentchen Co-authored-by: Geoffrey19 Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> Co-authored-by: Pepijn Co-authored-by: geoffrey --- docs/source/policy_walloss_README.md | 18 ++++++++++++++---- src/lerobot/policies/wall_x/modeling_wall_x.py | 2 +- 2 files changed, 15 insertions(+), 5 deletions(-) diff --git a/docs/source/policy_walloss_README.md b/docs/source/policy_walloss_README.md index 78548bd8d..93c0ad392 100644 --- a/docs/source/policy_walloss_README.md +++ b/docs/source/policy_walloss_README.md @@ -1,20 +1,30 @@ # WALL-OSS -This repository contains the Hugging Face port of **WALL-OSS**, a Vision-Language-Action model for cross-embodiment robotic control based on Qwen2.5-VL with flow matching/FAST action prediction. +This repository contains the Hugging Face port of [**WALL-OSS**](https://x2robot.com/en/research/68bc2cde8497d7f238dde690), a Vision-Language-Action model for cross-embodiment robotic control based on Qwen2.5-VL with flow matching/FAST action prediction. --- ## Model Overview | Feature | Description | -| ------------------ | ----------------------------------------------------- | --- | +| ------------------ | ----------------------------------------------------- | | Base Model | Qwen2.5-VL (Vision-Language Model) | | Action Prediction | Flow Matching (diffusion) or FAST (discrete tokens) | -| Architecture | Mixture of Experts (MoE) with action-specific routing | | +| Architecture | Mixture of Experts (MoE) with action-specific routing | | Multi-Modal Inputs | Vision (images/videos), Language, Proprioception | --- +## Additional Resources + +Paper: https://arxiv.org/pdf/2509.11766 + +Official Repository: https://github.com/X-Square-Robot/wall-x + +Hugging Face: https://huggingface.co/x-square-robot + +--- + ## Citation If you use this work, please cite: @@ -32,4 +42,4 @@ If you use this work, please cite: ## License -This port follows the **Apache 2.0 License**. +This model follows the **Apache 2.0 License**, consistent with the original [WallX repository](https://github.com/X-Square-Robot/wall-x). diff --git a/src/lerobot/policies/wall_x/modeling_wall_x.py b/src/lerobot/policies/wall_x/modeling_wall_x.py index c401c8d60..94ee7897e 100644 --- a/src/lerobot/policies/wall_x/modeling_wall_x.py +++ b/src/lerobot/policies/wall_x/modeling_wall_x.py @@ -1697,7 +1697,7 @@ class WallXPolicy(PreTrainedPolicy): config_class = WallXConfig name = "wall_x" - def __init__(self, config: WallXConfig): + def __init__(self, config: WallXConfig, **kwargs): super().__init__(config) config.validate_features() self.config = config