X
X SQUARE ROBOT / x-square-robot/wall-wm-2.0-robodojo

WALL-WM 2.0 RoboDojo Preview

X Square Robot released this pretrained checkpoint on November 21, 2026 as the starting point for RoboDojo training. It is a preview of WALL-WM 2.0, distinct from the full release, mainly in the number of training iterations. The repository provides weights, configuration and action and state normalization statistics. It is neither a conversational assistant nor a robot policy ready to connect to any machine.

01 / SUMMARY

The essential

ORIENTATIONWorld-action model pretraining

Primary use stated or inferred cautiously from official documentation.

CONTEXTPublished configuration: three views; text features of length 512

Maximum input capacity when published by the source.

EXIT20-dimensional action configuration and 32-step chunks

Documented maximum generation limit.

ACCESSHugging Face · downloadable checkpoint

Verified availability channels.

MODEL TYPERobotics · Multimodal

Primary functional family and verified specialties.

LICENSEApache 2.0

Declared terms for API access, model weights, or self-hosting.

02 / TECHNICAL SHEET

Limits and integration

API IDx-square-robot/wall-wm-2.0-robodojo
Model typeRobotics · Multimodal
Access modelOpen weights
LicenseApache 2.0
DeploymentSelf-hosted
Release21 NOV 2026
Knowledge cutoffNot published
EntranceText · Image · Robot state
ExitVideo and action representations
Context windowPublished configuration: three views; text features of length 512
maximum output20-dimensional action configuration and 32-step chunks
ReasoningNot published
Published tools
Structured OutingsNot published
Batch processingNot published
Prompt cacheNot published
Fine-tuningStarting point for RoboDojo training
Verified platformsHugging Face
BEST SUITED FOR

Research on world-action models and subsequent adaptation to robot manipulation. The configuration uses Wan2.2-TI2V-5B, and the card identifies the Qwen3.5-9B tokenizer and chat template. It defines three camera views and actions for both arms through relative positions, 6D rotations and grippers. These describe the training artifact; they do not certify compatibility with a particular robot or autonomous execution quality.

WORTH MONITORING

The weight file is about 24.1 GB; its size is not a VRAM requirement. Length 512 refers to text features in this configuration, not a universal conversation window. Pin the revision, review dependencies and normalization, and validate in simulation first. Training options do not establish that action inference is enabled or ready without adaptation. The full version and the WALL-OSS policy are different artifacts.

03 / CAPABILITIES

What it can do

01

Orientation

Research on world-action models and subsequent adaptation to robot manipulation. The configuration uses Wan2.2-TI2V-5B, and the card identifies the Qwen3.5-9B tokenizer and chat template. It defines three camera views and actions for both arms through relative positions, 6D rotations and grippers. These describe the training artifact; they do not certify compatibility with a particular robot or autonomous execution quality.

02

Context

Published configuration: three views; text features of length 512 · 20-dimensional action configuration and 32-step chunks

03

Tools and integration

Not published

04

Access

Hugging Face · downloadable checkpoint

Input modalities
TextImageRobot state
04 / PRICES

Documented cost

ConceptWorthUnit/condition
Standard inputNo published official API rateStandard API rate
Cached inputNot publishedReading reused prefixes
Cache write or storageNot publishedThe condition varies by provider
Standard outputSelf-hosted infrastructure costMay include reasoning tokens
Batch inputNot publishedAsynchronous processing
Batch outputNot publishedAsynchronous processing

The card declares Apache 2.0 for this downloadable checkpoint. No commercial endpoint or official tariffs have been verified for this version; numeric prices remain unpublished. Self-hosting consumes compute, memory and operations. The general WALL-WM code explains the architecture but does not by itself establish an identical training recipe for this preview.

i Prices change and may depend on level, region or context length. Check the source before making a decision.

05 / EVALUATIONS

How to read the results

“

No verified published scores are available for this exact checkpoint. Results from WALL-OSS, the original WALL-WM work or fine-tuned RoboDojo policies do not transfer to these pretrained weights. The 20 action components, 32-step chunks and file size are technical specifications, not measures of robot success. Performance comparisons require the same task, robot, fine-tuning and protocol.

i No verified published results for this preview checkpoint.

Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.

06 / VERSIONS

Chronology

x-square-robot/wall-wm-2.0-robodojo

Preview weights released; configuration updated on November 22.

07 / SOURCES

Traceability