yinchenghust

/

deepthinkvla_libero_cot_rl

like 0

Hi! I'm Niels, part of the community science team at Hugging Face. I've noticed this model repository is missing a model card. I've opened this PR to add a README that includes:

• The robotics pipeline tag and relevant metadata.
• Links to the DeepThinkVLA paper and official GitHub repository.
• A summary of the hybrid-attention decoder architecture and the training pipeline (SFT + RL).
• The BibTeX citation for the work.