First framework for interpreting 4D molecular trajectories into natural language explanations.
arXiv · March 13, 2026 · 2603.11924
Why it matters
While existing models focus on static chemistry, Chem4DLLM uses equivariant graph encoders to model bond breaking and formation in motion. This allows researchers to automate the mechanistic interpretation of chemical dynamics and catalytic reactions.
From the abstract
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, incl