paper-with-me

홈 › Papers

GTR-CoT: Graph Traversal as Visual Chain of Thought for Molecular Structure Recognition

2025-06-09 · JingChao Wang, Haote Yang, Jiang Wu, Yifan He, Xingjian Wei, Yinfan Wang, Chengjin Liu, Lingli Ge, Lijun Wu, Bin Wang, Dahua Lin, Conghui He

Optical Chemical Structure Recognition (OCSR) is crucial for digitizing chemical knowledge by converting molecular images into machine-readable formats. While recent vision-language models (VLMs) have shown potential in this task, their image-captioning approach often struggles with complex molecular structures and inconsistent annotations. To overcome these challenges, we introduce GTR-Mol-VLM, a novel framework featuring two key innovations: (1) the Graph Traversal as Visual Chain of Thought mechanism that emulates human reasoning by incrementally parsing molecular graphs through sequential atom-bond predictions, and (2) the data-centric principle of Faithfully Recognize What You've Seen, which addresses the mismatch between abbreviated structures in images and their expanded annotations. To support model development, we constructed GTR-CoT-1.3M, a large-scale instruction-tuning dataset with meticulously corrected annotations, and introduced MolRec-Bench, the first benchmark designed for a fine-grained evaluation of graph-parsing accuracy in OCSR. Comprehensive experiments demonstrate that GTR-Mol-VLM achieves superior results compared to specialist models, chemistry-domain VLMs, and commercial general-purpose VLMs. Notably, in scenarios involving molecular images with functional group abbreviations, GTR-Mol-VLM outperforms the second-best baseline by approximately 14 percentage points, both in SMILES-based and graph-based metrics. We hope that this work will drive OCSR technology to more effectively meet real-world needs, thereby advancing the fields of cheminformatics and AI for Science. We will release GTR-CoT at https://github.com/opendatalab/GTR-CoT.

📄 PDF Abstract BibTeX arXiv:2506.07553

Code (0)

등록된 구현이 없습니다.

Tasks

Image Captioning

Similar Papers 제목 키워드 기반

Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning

2025-11-11 · Tianwen Lyu, Xiang Zhuang, Keyan Ding, Xinzhe Cao 외 arxiv

Understanding complex biomolecular mechanisms requires multi-step reasoning across molecular interactions, signaling cascades, and metabolic pathways. While large language models(LLMs) show promise in such tasks, their a…

Reinforcement LearningQuestion Answering

Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data

2026-01-21 · Yuval Ran-Milo, Yotam Alexander, Shahar Mendel, Nadav Cohen arxiv

Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rew…

Reinforcement LearningMathematical Reasoning

RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals

2025-05-21 · Xuanliang Zhang, Dingzirui Wang, Keyan Xu, Qingfu Zhu 외

The table reasoning task, crucial for efficient data acquisition, aims to answer questions based on the given table. Recently, reasoning large language models (RLLMs) with Long Chain-of-Thought (Long CoT) significantly e…

The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning

2026-01-09 · Qiguang Chen, Yantao Du, Ziniu Li, Jinhao Liu 외 arxiv

Large language models (LLMs) often fail to learn effective long chain-of-thought (Long CoT) reasoning from human or non-Long-CoT LLMs imitation. To understand this, we propose that effective and learnable Long CoT trajec…

MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains

2025-08-25 · Kaiwen Wei, Rui Shan, Dongsheng Zou, Jianzhong Yang 외 arxiv

Large reasoning models (LRMs) have shown significant progress in test-time scaling through chain-of-thought prompting. Current approaches like search-o1 integrate retrieval augmented generation (RAG) into multi-step reas…

Knowledge Graphs