GreenVLA-5b-stride-1-R1-bridge

Embodiment-Adapted VLA for Bridge (WidowX)

Sber Robotics Center · Manipulation Team

Overview

GreenVLA-5b-stride-1-R1-bridge is the R1 (embodiment-adapted) checkpoint of the Green-VLA family, fine-tuned on the Bridge dataset for the WidowX robot arm.

Starting from the GreenVLA-5b-base-stride-1 pretrained checkpoint, this model was adapted via supervised fine-tuning (R1 stage) to the Bridge embodiment, achieving strong manipulation performance on the SimplerEnv benchmark.

Evaluation

Evaluated on SimplerEnv WidowX (Bridge) benchmark with default episode length.

Note: Bridge benchmark results can vary up to ±6% between runs. We recommend averaging over multiple evaluation runs for reliable comparisons.

Partial Success Rate

Task	Success Rate
Put Spoon on Towel	91.7%
Put Carrot on Plate	75.0%
Stack Blocks	91.7%
Put Eggplant in Basket	100.0%
Average	89.6%

Entire Success Rate

Task	Success Rate
Put Spoon on Towel	79.2%
Put Carrot on Plate	62.5%
Stack Blocks	58.3%
Put Eggplant in Basket	91.7%
Average	72.9%

Training

	Details
Base checkpoint	GreenVLA-5b-base-stride-1
Stage	R1 — Embodiment-specific adaptation
Method	Supervised fine-tuning
Dataset	IPEC-COMMUNITY/bridge_orig_lerobot
Robot	WidowX (Bridge)
Parameters	~5B

Quick Start

Installation

git clone https://github.com/greenvla/GreenVLA.git
cd GreenVLA
uv sync  # or: pip install -e .

Inference

import numpy as np
import torch
from lerobot.common.policies.factory import load_pretrained_policy
from lerobot.common.utils.torch_observation import (
    move_dict_to_batch_for_inference,
    torch_preprocess_dict_inference,
)

# 1. Load policy and transforms.
policy, input_transforms, output_transforms = load_pretrained_policy(
    "SberRoboticsCenter/GreenVLA-5b-stride-1-R1-bridge",
    data_config_name="bridge",
)
policy.to("cuda").eval()

# 2. Build an observation (replace with real sensor data).
raw_obs = {
    "observation/state": np.random.rand(8).astype(np.float32),  # x y z roll pitch yaw _pad_ gripper
    "observation/image": np.random.randint(0, 256, size=(224, 224, 3), dtype=np.uint8),
    "prompt": "pick up the green block and place it on the plate",
}

# 3. Transform, preprocess, and batch.
obs = input_transforms(raw_obs)
obs = torch_preprocess_dict_inference(obs)
batch = move_dict_to_batch_for_inference(obs, device="cuda")

# 4. Predict actions and post-process.
with torch.inference_mode():
    raw_actions = policy.select_action(batch).cpu().numpy()

actions = output_transforms(
    {"actions": raw_actions, "state": batch["state"].cpu().numpy()}
)["actions"]
# actions shape: (action_horizon, 7) — [x, y, z, roll, pitch, yaw, gripper]

See examples/example_inference_bridge.py for the full runnable script with argument parsing.

Citation

@misc{apanasevich2026greenvlastagedvisionlanguageactionmodel,
    title   = {Green-VLA: Staged Vision-Language-Action Model for Generalist Robots},
    author  = {I. Apanasevich and M. Artemyev and R. Babakyan and P. Fedotova and
               D. Grankin and E. Kupryashin and A. Misailidi and D. Nerus and
               A. Nutalapati and G. Sidorov and I. Efremov and M. Gerasyov and
               D. Pikurov and Y. Senchenko and S. Davidenko and D. Kulikov and
               M. Sultankin and K. Askarbek and O. Shamanin and D. Statovoy and
               E. Zalyaev and I. Zorin and A. Letkin and E. Rusakov and
               A. Silchenko and V. Vorobyov and S. Sobolnikov and A. Postnikov},
    year    = {2026},
    eprint  = {2602.00919},
    archivePrefix = {arXiv},
    primaryClass  = {cs.RO},
    url     = {https://arxiv.org/abs/2602.00919},
}