ChemVLR: Prioritizing Reasoning in Perception for Chemical Vision-Language Understanding

TL;DR

ChemVLR is a novel chemical vision-language model that emphasizes explicit reasoning by analyzing visual inputs with detailed chemical descriptors, leading to interpretable solutions and state-of-the-art performance.

Contribution

Introduces ChemVLR, a chemical VLM that prioritizes reasoning through fine-grained analysis and a new training framework, outperforming existing models.

Findings

ChemVLR surpasses leading proprietary and open-source models in chemical visual reasoning tasks.

The model produces explicit, interpretable reasoning paths for complex chemical problems.

A large-scale dataset of 760k samples was curated for training and evaluation.

Abstract

While Vision-Language Models (VLMs) have demonstrated significant potential in chemical visual understanding, current models are predominantly optimized for direct visual question-answering tasks. This paradigm often results in "black-box" systems that fail to utilize the inherent capability of Large Language Models (LLMs) to infer underlying reaction mechanisms. In this work, we introduce ChemVLR, a chemical VLM designed to prioritize reasoning within the perception process. Unlike conventional chemical VLMs, ChemVLR analyzes visual inputs in a fine-grained manner by explicitly identifying granular chemical descriptors, such as functional groups, prior to generating answers. This approach ensures the production of explicit and interpretable reasoning paths for complex visual chemical problems. To facilitate this methodology, we implement a cross-modality reverse-engineering strategy, combined with a rigorous filtering pipeline, to curate a large-scale reasoning-and-captioning dataset comprising 760k high-quality samples across molecular and reaction tasks. Furthermore, we adopt a three-stage training framework that systemically builds model perception and reasoning capacity. Experiments demonstrate that ChemVLR achieves state-of-the-art (SOTA) performance, surpassing both leading proprietary models and domain-specific open-source baselines. We also provide comprehensive ablation studies to validate our training strategy and data generation designs. Code and model weights will be available at https://github.com/xxlllz/ChemVLR.