Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,129 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- Qwen/Qwen2.5-VL-7B-Instruct
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- chart-to-code
+- multimodal
+- vision-language
+- reinforcement-learning
+- self-correction
+- matplotlib
+---
+
+# MM-ReCoder
+
+<p align="center">
+  <a href="https://cvpr.thecvf.com/Conferences/2026"><b>CVPR 2026</b></a>
+  &nbsp;|&nbsp;
+  <a href="https://zitiantang.github.io/MM-ReCoder/">Project Page</a>
+  &nbsp;|&nbsp;
+  <a href="https://arxiv.org/abs/2604.01600">arXiv</a>
+  &nbsp;|&nbsp;
+  <a href="https://github.com/ZitianTang/MM-ReCoder">Code</a>
+  &nbsp;|&nbsp;
+  <a href="https://huggingface.co/cwbc/MM-ReCoder-SFT-Cold-Start">SFT Cold-Start</a>
+</p>
+
+**MM-ReCoder** is the 7B vision-language model from the CVPR 2026 paper
+[*MM-ReCoder: Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correction*](https://arxiv.org/abs/2604.01600).
+It converts a chart image into the matplotlib code that reproduces it. At
+inference time the model renders its own code with a sandboxed matplotlib
+tool, inspects the result, and self-corrects across multiple turns.
+
+This is the **final** RL-trained checkpoint. It is fine-tuned from
+[`Qwen/Qwen2.5-VL-7B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)
+via:
+
+1. **SFT cold-start** — released separately as
+   [`cwbc/MM-ReCoder-SFT-Cold-Start`](https://huggingface.co/cwbc/MM-ReCoder-SFT-Cold-Start).
+2. **Multi-turn RL (GRPO), stage 1** — shared-first-turn optimization.
+3. **Multi-turn RL (GRPO), stage 2** — full-trajectory optimization,
+   resumed from stage 1.
+
+## Usage
+
+The recommended way to use MM-ReCoder is through the inference scripts in
+the [official repository](https://github.com/ZitianTang/MM-ReCoder), which
+wrap the model with the self-correction agent loop (render → critique →
+revise):
+
+```bash
+git clone https://github.com/ZitianTang/MM-ReCoder.git
+cd MM-ReCoder
+# Follow the Installation section in the repo README.
+
+# Downalod the MM-ReCoder checkpoint from Hugging Face
+hf download cwbc/MM-ReCoder
+
+# Two-turn self-correction on ChartMimic.
+bash examples/mmrecoder/inference/chartmimic_2turns.sh
+```
+
+### Direct single-turn use (no self-correction)
+
+You can also load the model in a single-pass setting via `transformers`:
+
+```python
+from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
+from PIL import Image
+import torch
+
+model_id = "cwbc/MM-ReCoder"
+processor = AutoProcessor.from_pretrained(model_id)
+model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+    model_id, torch_dtype=torch.bfloat16, device_map="auto"
+)
+
+image = Image.open("path/to/chart.png").convert("RGB")
+messages = [{
+    "role": "user",
+    "content": [
+        {"type": "image", "image": image},
+        {"type": "text", "text": "Generate the matplotlib code that reproduces this chart."},
+    ],
+}]
+text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device)
+
+out = model.generate(**inputs, max_new_tokens=4096, do_sample=False)
+print(processor.batch_decode(out[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)[0])
+```
+
+This emits code in one shot. The full self-correction behavior requires the
+agent loop in the repository.
+
+## Training
+
+- **Base model:** Qwen2.5-VL-7B-Instruct.
+- **RL algorithm:** GRPO with chart-specific rule-based rewards (format,
+  color, text, layout, type) plus an LLM-as-a-judge model reward.
+- **RL data:** [Chart2Code-160k](https://huggingface.co/datasets/xxxllz/Chart2Code-160k)
+  prompts.
+- **Evaluation:**
+  [ChartMimic](https://github.com/ChartMimic/ChartMimic) (direct-600),
+  [Plot2Code](https://github.com/TencentARC/Plot2Code), and
+  [ChartX](https://github.com/InternScience/ChartVLM).
+
+See the [repository](https://github.com/ZitianTang/MM-ReCoder) for full
+training scripts and configs.
+
+## Citation
+
+```bibtex
+@inproceedings{tang2026mmrecoder,
+    title={MM-ReCoder: Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correction},
+    author={Zitian Tang and Xu Zhang and Jianbo Yuan and Yang Zou and Varad Gunjal and Songyao Jiang and Davide Modolo},
+    booktitle={CVPR},
+    year={2026}
+}
+```
+
+## License
+
+Released under the Apache 2.0 License, inheriting from the base
+Qwen2.5-VL-7B-Instruct license.