Tsinghua University AIR
lab · ChinaScores
1 product on the map — 1 open-ish.
Openness
3 high confidence- weights
- open (X-VLA-Pt and its fine-tunes on the Hub, ungated)
- data
- described (the cross-embodiment pretraining mixture is not published, though the repository ships readers for DROID, RoboMind and AgiBot World)
- code
- open (training script, dataset handlers and LoRA fine-tuning code)
- license
- Apache-2.0 (code and weights)
X-VLA's weights and training code are Apache-2.0. The repository can read the public robot datasets it trained on, but the assembled pretraining mixture is not published.
- https://huggingface.co/2toINF/X-VLA-Pt/raw/main/README.md recorded 2026-11-12
X-VLA-Pt card: license apache-2.0, base_model microsoft/Florence-2-large, "X-VLA 0.9B (Foundation Edition)".
- https://huggingface.co/api/models?author=2toINF&limit=100&expand[]=downloads&expand[]=cardData&expand[]=gated&expand[]=createdAt recorded 2026-11-12
X-VLA-Pt and nine full fine-tunes (2025-11), gated false and tagged apache-2.0.
- https://raw.githubusercontent.com/2toinf/X-VLA/main/LICENSE recorded 2026-11-12
LICENSE: Apache License, Version 2.0.
- https://raw.githubusercontent.com/2toinf/X-VLA/main/README.md recorded 2026-11-12
README: "This repository is licensed under the Apache License 2.0"; training with accelerate through train.py on custom data; LoRA fine-tuning code released.
- https://ungh.cc/repos/2toinf/X-VLA/files/main recorded 2026-11-12
Repository tree: datasets/domain_handler/droid.py, robomind.py, agiworld.py, lerobot_agibot.py and x2robot.py; no dataset files.
Adoption
1 medium confidenceHugging Face downloads over the trailing 30 days for the foundation checkpoint and five full fine-tunes, most of them for the foundation model. LeRobot's converted copies are downloaded separately and are not counted.
- https://huggingface.co/api/models?author=2toINF&limit=100&expand[]=downloads&expand[]=cardData&expand[]=gated&expand[]=createdAt recorded 2026-11-12
X-VLA-Pt 7,803, X-VLA-Libero 840, X-VLA-RoboTwin2 478, X-VLA-SoftFold 389, X-VLA-WidowX 205 and X-VLA-Google-Robot 43 downloads in the trailing 30 days (9,758 together).
Capability
4 medium confidenceX-VLA is pretrained across robot bodies and ships two-armed policies, including one for folding cloth, level with GR00T. It has no separate reasoning model and no humanoid control.
- https://arxiv.org/abs/2510.10274 recorded 2026-11-12
Abstract: soft prompts as "embodiment-specific prompts" for cross-embodiment training; evaluated across 6 simulations and 3 real-world robots.
- https://raw.githubusercontent.com/2toinf/X-VLA/main/README.md recorded 2026-11-12
README: X-VLA-0.9B "achieves state-of-the-art generalization across six simulation platforms and three real-world robots"; X-VLA-RoboTwin2 "for dual-arm coordinated manipulation"; X-VLA-SoftFold "Specialized in deformable object manipulation (e.g., folding and cloth control)".