Add model card and metadata

README.md

@@ -0,0 +1,42 @@
+---
+pipeline_tag: image-text-to-text
+---
+
+# BARD-VL
+
+BARD (Bridging AutoRegressive and Diffusion) is a framework that converts a pretrained autoregressive Vision-Language Model (VLM) into a decoding-efficient diffusion VLM (dVLM) through progressive block merging and stage-wise distillation.
+
+- **Paper:** [BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation](https://huggingface.co/papers/2604.16514)
+- **Code:** [GitHub Repository](https://github.com/fudan-generative-vision/Bard-VL)
+- **Project Page:** [https://fudan-generative-vision.github.io/Bard-VL](https://fudan-generative-vision.github.io/Bard-VL)
+
+## Description
+
+Autoregressive VLMs deliver strong multimodal capability, but their token-by-token decoding imposes a fundamental inference bottleneck. BARD-VL addresses this by converting a pretrained autoregressive VLM into a same-architecture, decoding-efficient dVLM. It establishes a new SOTA among comparable-scale open dVLMs while achieving up to 3× decoding throughput speedup compared to the source model.
+
+## Inference
+
+The official repository provides an `inference.py` script for image and video understanding. To run inference, clone the repository and use the following command as a template:
+
+```bash
+python3 inference.py \
+  --model_id fudan-generative-ai/Bard-VL-B4-Mask-8B-Instruct \
+  --block_size 4 \
+  --denoising_steps 4 \
+  --confidence_threshold 0.6
+```
+
+## Citation
+
+```bibtex
+@article{chen2026bard,
+  title={BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation},
+  author={Chen, Baoyou and Xia, Hanchen and Tu, Peng and Shi, Haojun and Mu, Shan and Yuan, Weihao and Zhu, Siyu},
+  journal={arXiv preprint arXiv:2604.16514},
+  year={2026}
+}
+```
+
+## Acknowledgements
+
+This repository builds on top of [NVIDIA NeMo AutoModel](https://github.com/NVIDIA-NeMo/Automodel).