Chem4DLLM: 4D Multimodal LLMs for Chemical Dynamics Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908881930682368 |
|---|---|
| author | Li, Xinyu Zhang, Zhen Chen, Qi Hengel, Anton van den Yao, Lina Shi, Javen Qinfeng |
| author_facet | Li, Xinyu Zhang, Zhen Chen, Qi Hengel, Anton van den Yao, Lina Shi, Javen Qinfeng |
| contents | Existing chemical understanding tasks primarily rely on static molecular representations, limiting their ability to model inherently dynamic phenomena such as bond breaking or conformational changes, which are essential for a chemist to understand chemical reactions. To address this gap, we introduce Chemical Dynamics Understanding (ChemDU), a new task that translates 4D molecular trajectories into interpretable natural-language explanations. ChemDU focuses on fundamental dynamic scenarios, including gas-phase and catalytic reactions, and requires models to reason about key events along molecular trajectories, such as bond formation and dissociation, and to generate coherent, mechanistically grounded narratives. To benchmark this capability, we construct Chem4DBench, the first dataset pairing 4D molecular trajectories with expert-authored explanations across these settings. We further propose Chem4DLLM, a unified model that integrates an equivariant graph encoder with a pretrained large language model to explicitly capture molecular geometry and rotational dynamics. We hope that ChemDU, together with Chem4DBench and Chem4DLLM, will stimulate further research in dynamic chemical understanding and multimodal scientific reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_11924 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Chem4DLLM: 4D Multimodal LLMs for Chemical Dynamics Understanding Li, Xinyu Zhang, Zhen Chen, Qi Hengel, Anton van den Yao, Lina Shi, Javen Qinfeng Machine Learning Computation and Language Existing chemical understanding tasks primarily rely on static molecular representations, limiting their ability to model inherently dynamic phenomena such as bond breaking or conformational changes, which are essential for a chemist to understand chemical reactions. To address this gap, we introduce Chemical Dynamics Understanding (ChemDU), a new task that translates 4D molecular trajectories into interpretable natural-language explanations. ChemDU focuses on fundamental dynamic scenarios, including gas-phase and catalytic reactions, and requires models to reason about key events along molecular trajectories, such as bond formation and dissociation, and to generate coherent, mechanistically grounded narratives. To benchmark this capability, we construct Chem4DBench, the first dataset pairing 4D molecular trajectories with expert-authored explanations across these settings. We further propose Chem4DLLM, a unified model that integrates an equivariant graph encoder with a pretrained large language model to explicitly capture molecular geometry and rotational dynamics. We hope that ChemDU, together with Chem4DBench and Chem4DLLM, will stimulate further research in dynamic chemical understanding and multimodal scientific reasoning. |
| title | Chem4DLLM: 4D Multimodal LLMs for Chemical Dynamics Understanding |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2603.11924 |