发表机构
The Hong Kong University of Science and Technology; The Chinese University of Hong Kong; University of Edinburgh（香港科技大学; 香港中文大学; 爱丁堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出MechaVLM视觉框架，结合可迁移化学表示与外部机制知识，通过多尺度接地和跨渲染对比学习，在零样本机制预测上显著提升性能，并引入MechBench基准。
AI 中文摘要
反应机制描述了化学反应背后的逐步转化过程，是反应分析和合成的核心。基于学习的模型已在既有机制预测基准上取得了强劲性能，但将其迁移到未见过的化学体系仍具挑战性。这种迁移之所以困难，是因为熟悉的机制必须应用于不熟悉的分子结构，且某些目标机制在训练数据中可能覆盖不足。为应对这些挑战，我们提出了MechaVLM，一个结合可迁移化学表示与外部机制知识的视觉框架。它通过多尺度化学接地和跨渲染对比学习来学习可复用的视觉特征。对于开卷预测，MechaVLM从70,384个文献机制图中检索固定集合的先例，并随着分子状态演化重新阅读相关视觉证据，直接使用图形而无需符号机制解析。随后，一个原子索引的语言解码器递归生成可执行的电子编辑，以构建完整机制。我们进一步引入了MechBench，一个具有挑战性的文献衍生基准，包含2,184个机制和9,146个基本步骤。在跨数据集和文献衍生基准上，MechaVLM建立了强大的零样本机制预测能力。其仅闭卷模型在FlowER到ReactMech迁移中，Step/Pathway Top-1分别提升了12.50/13.93个百分点，而外部视觉先例进一步在具有挑战性的分布外反应上带来增益。学习到的表示还泛化到机制预测之外的原子映射和反应中心预测。
英文摘要
Reaction mechanisms describe the step-by-step transformations underlying chemical reactions and are central to reaction analysis and synthesis. Learning-based models have achieved strong performance on established mechanism-prediction benchmarks, but transferring them to unseen chemistry remains challenging. Such transfer is difficult because familiar mechanisms must be applied to unfamiliar molecular structures, and some target mechanisms may be poorly covered by the training data. To address these challenges, we introduce MechaVLM, a visual framework that combines transferable chemical representations with external mechanistic knowledge. It learns reusable visual features through multiscale chemical grounding and cross-rendering contrastive learning. For open-book prediction, MechaVLM retrieves a fixed set of precedents from 70,384 literature mechanism figures and re-reads relevant visual evidence as the molecular state evolves, directly using the figures without symbolic mechanism parsing. An atom-indexed language decoder then recursively generates executable electron edits to construct the complete mechanism. We further introduce MechBench, a challenging literature-derived benchmark with 2,184 mechanisms and 9,146 elementary steps. Across cross-dataset and literature-derived benchmarks, MechaVLM establishes strong zero-shot mechanism prediction. Its closed-book model alone improves Step/Pathway Top-1 by 12.50/13.93 percentage points on FlowER-to-ReactMech transfer, while external visual precedents unlock further gains on challenging OOD reactions. The learned representation also generalizes beyond mechanism prediction to atom mapping and reaction center prediction.
