Add model card for DeepThinkVLA

This PR adds a comprehensive model card for DeepThinkVLA. It includes:
- A link to the paper: [DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models](https://huggingface.co/papers/2511.15669).
- A link to the official GitHub repository.
- The `robotics` pipeline tag to improve discoverability on the Hub.
- Information regarding the model's hybrid-attention architecture and performance results on the LIBERO benchmark.

README.md

@@ -0,0 +1,43 @@
+---
+pipeline_tag: robotics
+---
+
+# DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
+
+DeepThinkVLA is a Vision-Language-Action (VLA) model designed to enhance the reasoning capabilities of robotic agents through explicit deliberation (Chain-of-Thought). It refactors the policy into a hybrid-attention decoder that separates autoregressive reasoning from parallel action generation.
+
+- **Paper:** [DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models](https://huggingface.co/papers/2511.15669)
+- **Repository:** [https://github.com/OpenBMB/DeepThinkVLA](https://github.com/OpenBMB/DeepThinkVLA)
+
+## Overview
+DeepThinkVLA introduces two key innovations for effective Chain-of-Thought (CoT) in robotics:
+1. **Decoding Alignment:** A hybrid-attention decoder that pairs causal attention for language (reasoning tokens) with bidirectional attention for parallel action decoding.
+2. **Causal Alignment:** A two-stage SFT-then-RL pipeline that aligns the reasoning-action chain with sparse task-success rewards, ensuring that the generated "thoughts" are causally linked to task success.
+
+The model achieves a 97.0% success rate on the LIBERO benchmark and demonstrates strong robustness under distribution shifts in LIBERO-Plus (79.0% zero-shot success).
+
+## Architecture
+DeepThinkVLA inserts a `<think>` segment between visual observations and robot actions. Starting from the `pi0-FAST` checkpoint, it uses a 2.9B parameter hybrid decoder. Reasoning tokens are generated autoregressively, after which the model switches to parallel decoding for action chunks to maintain low latency.
+
+## Performance
+- **LIBERO:** 97.0% average success rate (Object 99.0, Spatial 96.6, Goal 96.4, Long 96.2).
+- **LIBERO-Plus:** 79.0% zero-shot robustness.
+- **RoboTwin 2.0:** 59.3% success rate.
+
+## Setup and Evaluation
+Please refer to the [official GitHub repository](https://github.com/OpenBMB/DeepThinkVLA) for detailed instructions on environment setup, dataset acquisition, and running evaluation scripts.
+
+Example evaluation command:
+```bash
+bash scripts/eval.sh --pretrained_checkpoint yinchenghust/deepthinkvla_libero_cot_sft
+```
+
+## Citation
+```bibtex
+@article{yin2025deepthinkvla,
+  title={DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models},
+  author={Yin, Cheng and Lin, Yankai and Xu, Wang and Tam, Sikyuen and Zeng, Xiangrui and Liu, Zhiyuan and Yin, Zhouping},
+  journal={arXiv preprint arXiv:2511.15669},
+  year={2025}
+}
+```