Fine-Tuning Vision-Language Models for Multimodal Polymer Property Prediction

TL;DR

This paper introduces a multimodal dataset and fine-tuning approach for vision-language models to improve polymer property prediction, showing that multimodal learning enhances performance and reduces model maintenance.

Contribution

The work presents a new multimodal polymer dataset and demonstrates effective fine-tuning of VLMs for scientific property prediction, highlighting the advantages of multimodal learning in materials science.

Findings

Fine-tuned models outperform unimodal baselines

Multimodal learning improves prediction accuracy

Reduces need for multiple property-specific models

Abstract

Vision-Language Models (VLMs) have shown strong performance in tasks like visual question answering and multimodal text generation, but their effectiveness in scientific domains such as materials science remains limited. While some machine learning methods have addressed specific challenges in this field, there is still a lack of foundation models designed for broad tasks like polymer property prediction using multimodal data. In this work, we present a multimodal polymer dataset to fine-tune VLMs through instruction-tuning pairs and assess the impact of multimodality on prediction performance. Our fine-tuned models, using LoRA, outperform unimodal and baseline approaches, demonstrating the benefits of multimodal learning. Additionally, this approach reduces the need to train separate models for different properties, lowering deployment and maintenance costs.