MolDA: Molecular Understanding and Generation via Large Language Diffusion Model
This work addresses the challenge of reliable molecular generation for drug discovery and materials science, representing an incremental improvement over existing multimodal architectures.
The paper tackled the problem of generating chemically valid molecules by addressing the limitations of autoregressive models, which struggle with global constraints and accumulate errors, and proposed MolDA, a framework using a discrete Large Language Diffusion Model that achieved improved structural coherence and validity across generation, captioning, and property prediction tasks.
Large Language Models (LLMs) have significantly advanced molecular discovery, but existing multimodal molecular architectures fundamentally rely on autoregressive (AR) backbones. This strict left-to-right inductive bias is sub-optimal for generating chemically valid molecules, as it struggles to account for non-local global constraints (e.g., ring closures) and often accumulates structural errors during sequential generation. To address these limitations, we propose MolDA (Molecular language model with masked Diffusion with mAsking), a novel multimodal framework that replaces the conventional AR backbone with a discrete Large Language Diffusion Model. MolDA extracts comprehensive structural representations using a hybrid graph encoder, which captures both local and global topologies, and aligns them into the language token space via a Q-Former. Furthermore, we mathematically reformulate Molecular Structure Preference Optimization specifically for the masked diffusion. Through bidirectional iterative denoising, MolDA ensures global structural coherence, chemical validity, and robust reasoning across molecule generation, captioning, and property prediction.