Unitree RoboticsChina2026

UnifoLM-WLA-1.0

An AI model: a vision-language-action model (VLA) takes camera images and an instruction and turns them into movements for a robot. This page describes the software, not a robot.

RobotsG1by Unitree Robotics A

Key figures as stated by the developer

6 of 6 stated

Model type ⁠A vision-language-action
Controls ⁠A arms and hands whole body
Inputs ⁠A camera language robot state
Access ⁠B open download
Parameters ⁠A 6,000,000,000
Base model ⁠A UnifoLM-ER-Flow

How to read the figures

14kgA30.9lbA: The letter in the grey square after a figure points to the source the figure came from. Robots with several sources carry several letters.
1,100mmB43.3inB: A dashed letter marks a secondary source – a datasheet, manual or developer documentation from the manufacturer, or a press report used only where the manufacturer gives no figure.
74.5lb: Imperial figures are our own conversion unless the manufacturer states an imperial figure itself. The source letter always belongs to the metric figure — a conversion has no source of its own.

The four states

Versions and notes in the key figures (6)

Model type

Developer wording: "6B VLA parameters".

Controls

"a single model coordinates 64 tasks spanning desktop manipulation and whole-body manipulation". "We partition the unified action space into three components: end-effector (EEF) poses, end-effector joints, and lower-body joints".

Inputs

Labels in the architecture diagram: "Image encoder Prompt State"

Access

GitHub release note: "we released the UnifoLM-WLA-1.0-Base and fine-tuning code"

Parameters

Unitree's total for the model: "general-purpose humanoid robot foundation model with 6B parameters"

Base model

"UnifoLM-WLA-1.0 builds on the UnifoLM-ER-Flow multimodal backbone and incorporates an MMDiT action expert". "Building on UnifoLM-ER-1, we introduce discrete action tokens and mask tokens for future dynamic regions". "Built on Qwen3-VL-4B, UnifoLM-ER-1 is trained on more than 5 million samples".

Full specifications

7 of 12 fields stated

The letter points to the source at the foot of the page. Fields without a figure are dashed: the developer does not state them — that is not the same as zero, and not the same as no.
Field	Value	Source and caveats
Input and output
Model type	`vision-language-action`	A Developer wording: "6B VLA parameters".
Inputs	`camera` `language` `robot state`	A Labels in the architecture diagram: "Image encoder Prompt State"
Controls	`arms and hands` `whole body`	A "a single model coordinates 64 tasks spanning desktop manipulation and whole-body manipulation". "We partition the unified action space into three components: end-effector (EEF) poses, end-effector joints, and lower-body joints".
Degrees of freedom controlled	not stated
Size and speed
Parameters	6,000,000,000	A Unitree's total for the model: "general-purpose humanoid robot foundation model with 6B parameters"
Control rate	not stated
Where it runs and what it is built on
Runs where	not stated
Base model	UnifoLM-ER-Flow	A "UnifoLM-WLA-1.0 builds on the UnifoLM-ER-Flow multimodal backbone and incorporates an MMDiT action expert". "Building on UnifoLM-ER-1, we introduce discrete action tokens and mask tokens for future dynamic regions". "Built on Qwen3-VL-4B, UnifoLM-ER-1 is trained on more than 5 million samples".
Openness
Access	open download	B GitHub release note: "we released the UnifoLM-WLA-1.0-Base and fine-tuning code"
License	Apache License 2.0	B "this project is released under the Apache License 2.0"; the Hugging Face model page shows "License: apache-2.0".
The developer’s own claims
Learns new tasks	not stated
Works across robots	not stated	Note Unitree reports "strong generalization across tasks and end effectors" and "Real-robot tests · Unitree G1". ⁠A Yes only if the developer itself says the model runs on different robot models, for example robots from two manufacturers or two of one manufacturer’s models. Several units of the same robot do not count.

Notes

Unitree describes UnifoLM-WLA-1.0 as a comprehensively upgraded, next-generation general-purpose humanoid robot foundation model with 6B parameters.

Sources

A Manufacturer product page. unigen-x.github.io/unifolm-wla.github.io/ · Retrieved 2026-10-13
B Secondary: github.com/unitreerobotics/unifolm-wla · Retrieved 2026-10-13

One line per source, not per figure: a source has one retrieval date. The letter beside a figure points to the line it came from.