Models and checkpoints

ARPO UI-TARS-1.5-7B checkpoint

UI-TARS-1.5-7B-derived checkpoint trained with ARPO on OSWorld desktop tasks.

AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.

Original source ↗Read as Markdown Record JSON

What is this resource?

Resource type: Models and checkpoints
Environment: desktop, linux
Topics: reinforcement-learning, action-prediction
Record publication date: Not recorded
Evidence retrieved: 2026-10-18T04:27:12Z
Resource ID: url:db6fc5f29f186d13991c

What licenses are recorded?

Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.

Code: Not recorded
Data: Not recorded
Document: Not recorded
Weights: Not recorded

License review notes

Weights: The inspected model card contains no checkpoint-license declaration. The code repository Apache license is not transferred to weights. Source 1

Recorded specifications

disabled: false
download url: https://huggingface.co/Fanbin/ARPO_UITARS1.5_7B/tree/2c5604d86c529843ef346698edcf33b170c1e817
gated: false
hub id: Fanbin/ARPO_UITARS1.5_7B
hub revision: 2c5604d86c529843ef346698edcf33b170c1e817
repository url: https://github.com/JIA-Lab-research/ARPO

Explore related topics

Reinforcement learning Action prediction

Scope and limitations

The public Hub manifest lists four Safetensors shards, an index and configuration/tokenizer files. The model card reports a 15-step evaluation setting; no performance result is independently reproduced. No weight license is declared, despite Apache-2.0 being established for the separate code repository.

Related resources

documented by: ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay

Primary evidence and verification

Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.

editorial primary review
Retrieved 2026-10-18T04:27:12Z. Supports: name, kind, summary, environments, topics, scope, notes, relations.
Content fingerprint
839b2de0e0c614fe8d2df4782d0f6a6e7d33f5c60d8020c9d4a01c61d533f39e
editorial primary review
Retrieved 2026-10-18T04:33:21Z. Supports: identity, release_status, details.hub_id, details.hub_revision, details.gated, details.disabled, details.download_url.
Content fingerprint
6e19a5339c4e52ca3753cce26ac2034883b96f5cb26383a4b41bc87a5fbf5bf6
editorial primary review
Retrieved 2026-10-18T04:35:16Z. Supports: summary, notes, licenses.weights.
Content fingerprint
b6957fad37a7995e9dde4c7d4a4e0f6e2153b85354b2d234587c2a94ff95d0bd

Suggest a correction

Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.