Saved in:
Bibliographic Details
Main Authors: Liu, Quanliang, Kim, Jungtaek, Lee, Kangwook, Oh, Hyunseok
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.07145
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917471377686528
author Liu, Quanliang
Kim, Jungtaek
Lee, Kangwook
Oh, Hyunseok
author_facet Liu, Quanliang
Kim, Jungtaek
Lee, Kangwook
Oh, Hyunseok
contents Vision-language models (VLMs) have shown strong potential for scientific image understanding, but general-purpose models often lack the domain-specific visual knowledge required for reliable materials characterization. In this work, we fine-tuned an open-source VLM (Qwen3-VL-32B-Instruct) for fracture-surface image analysis using a curated dataset of 13,168 open-source, literature-mined fracture-surface images. Morphology annotations were generated by GPT-5.2-Reasoning (high) from both the images and relevant excerpts of their source papers, and the dataset was further enriched with targeted manual collection and rotation-based augmentation. The resulting specialist model outperforms flagship proprietary multimodal models on a benchmark of 100 manually annotated images. It achieves a precision of 0.92, compared to 0.35 for the base Qwen3-VL-32B-Instruct, 0.58 for GPT-5.5-Reasoning (high), and 0.78 for Gemini 3.1 Pro-Reasoning (high). Dataset ablations show that manual collection of rare-feature images and augmentation via image rotation are both beneficial to improve recognition of less common fracture morphology features. We further discuss integrated use of the fine-tuned model with proprietary models to combine fracture-specific visual accuracy with broader multimodal reasoning for autonomous fractography. Although focused on fracture-surface images, this work demonstrates how VLMs can be adapted through targeted collection and fine-tuning on novel feature images to recognize those features and support downstream decision-making in autonomous microscopy workflows.
format Preprint
id arxiv_https___arxiv_org_abs_2605_07145
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fine-tuning a vision-language model for fracture-surface morphology recognition
Liu, Quanliang
Kim, Jungtaek
Lee, Kangwook
Oh, Hyunseok
Materials Science
Computer Vision and Pattern Recognition
Vision-language models (VLMs) have shown strong potential for scientific image understanding, but general-purpose models often lack the domain-specific visual knowledge required for reliable materials characterization. In this work, we fine-tuned an open-source VLM (Qwen3-VL-32B-Instruct) for fracture-surface image analysis using a curated dataset of 13,168 open-source, literature-mined fracture-surface images. Morphology annotations were generated by GPT-5.2-Reasoning (high) from both the images and relevant excerpts of their source papers, and the dataset was further enriched with targeted manual collection and rotation-based augmentation. The resulting specialist model outperforms flagship proprietary multimodal models on a benchmark of 100 manually annotated images. It achieves a precision of 0.92, compared to 0.35 for the base Qwen3-VL-32B-Instruct, 0.58 for GPT-5.5-Reasoning (high), and 0.78 for Gemini 3.1 Pro-Reasoning (high). Dataset ablations show that manual collection of rare-feature images and augmentation via image rotation are both beneficial to improve recognition of less common fracture morphology features. We further discuss integrated use of the fine-tuned model with proprietary models to combine fracture-specific visual accuracy with broader multimodal reasoning for autonomous fractography. Although focused on fracture-surface images, this work demonstrates how VLMs can be adapted through targeted collection and fine-tuning on novel feature images to recognize those features and support downstream decision-making in autonomous microscopy workflows.
title Fine-tuning a vision-language model for fracture-surface morphology recognition
topic Materials Science
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.07145