MechVL-4B-SFT

The SFT checkpoint of MechVL — the domain-specialized multimodal model for mechanical engineering drawing understanding, introduced in:

MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding (ICML 2026)

Model description

MechVL-4B-SFT is initialized from Qwen3-VL-4B-Instruct and trained with full-parameter SFT on the LLM module (vision encoder & projection frozen) over the MechVQA training split. It serves as the reference policy (π_ref) for the subsequent RL stage.


Base model	Qwen3-VL-4B-Instruct
Architecture	Qwen3VLForConditionalGeneration
Stage	1 / 2 — SFT (→ RL)
MechVQA Total	76.36
RL checkpoint	MonteXiaofeng/MechVL-4B-RL

Usage (transformers)

import torch
from transformers import AutoProcessor, AutoModelForImageTextToText

model = AutoModelForImageTextToText.from_pretrained(
    "MonteXiaofeng/MechVL-4B-SFT", dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("MonteXiaofeng/MechVL-4B-SFT")

messages = [{"role": "user", "content": [
    {"type": "image", "url": "path/to/drawing.png"},
    {"type": "text", "text": "图纸中标注的零件总长度是多少？"},
]}]
inputs = processor.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=True,
    return_dict=True, return_tensors="pt",
).to(model.device)
out = model.generate(**inputs, max_new_tokens=1024)
print(processor.decode(out[0], skip_special_tokens=True))

For batch vLLM inference (SFT/RL dual-mode), see scripts/batch_infer.py.

Training

Full-parameter SFT on the LLM module (vision tower frozen) over the MechVQA training split, with a unified response schema (rationale + concise final answer). See §4.1 of the paper.

Citation

@misc{kou2026mechvqabenchmarkingenhancingmultimodal,
      title={MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding},
      author={Qian Kou and Xiaofeng Shi and Yulin Li and Xiaosong Qiu and Xinyang Wang and Hua Zhou and Cao Dongxing},
      year={2026},
      eprint={2605.30794},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2605.30794}
}