Input: 8 third-person frames, 8 wrist-camera frames, 8-D proprioception, and a natural-language instruction
Reasoning: one episode-level Plan and one chunk-level Think span
Output: an 8-step action chunk with 7 action dimensions per step
Training: two epochs on the union of the four LIBERO-Plus suites
Final checkpoint step: 102,024

Results

LIBERO-Plus

Suite	Success rate
Spatial	90.8%
Object	87.3%
Goal	86.6%
Long	80.7%

Standard LIBERO

Suite	Success rate
Spatial	99.4%
Object	100.0%
Goal	98.6%
Long	92.0%
Average	97.5%

Files

student_state_dict.pt: complete policy state dictionary
action_head_config.json: policy and reasoning-token configuration
tokenizer and processor files: multimodal preprocessing and added tokens
release_info.json: release metadata
SHA256SUMS: file-integrity checksums

Usage

This checkpoint uses a custom policy class and is not directly loadable with AutoModel.from_pretrained.

Download the checkpoint with:

hf download euphoria-64/CoTinyVLA-Qwen3.5-0.8B --local-dir checkpoints/cotinyvla

Training, inference, and evaluation code:

https://github.com/BrainJellyPie/CoTinyVLA

Limitations

Evaluation is limited to LIBERO and LIBERO-Plus simulation.
Sim-to-real and cross-embodiment transfer have not been evaluated.
The current implementation uses synchronous reasoning generation.
Physical-robot deployment requires additional safety validation.

License and third-party resources

This repository does not redistribute LIBERO or LIBERO-Plus datasets, assets, or environment code. Users must obtain them from their original sources and follow their respective licenses.

The final checkpoint license will be specified before public release.

Paper

CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model

Minhyeok Lee, Chiyoung Kim, Chanhoe Gu, Seongrok Kim, Sanghyuk Roy Choi, Donghwan Hwang, Donghun Ryu, and Seokhyun Kim.

Paper: https://arxiv.org/abs/2607.25487
DOI: https://doi.org/10.48550/arXiv.2607.25487
Code: https://github.com/BrainJellyPie/CoTinyVLA

Citation

Please cite the following paper when using this checkpoint:

@article{lee2026cotinyvla,
  title   = {CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model},
  author  = {Lee, Minhyeok and Kim, Chiyoung and Gu, Chanhoe and Kim, Seongrok and Choi, Sanghyuk Roy and Hwang, Donghwan and Ryu, Donghun and Kim, Seokhyun},
  journal = {arXiv preprint arXiv:2607.25487},
  year    = {2026},
  doi     = {10.48550/arXiv.2607.25487},
  url     = {https://arxiv.org/abs/2607.25487}
}