Bridging molecular structures and natural language is essential for controllable design. Autoregressive models struggle with long-range dependencies, while standard diffusion processes apply uniform corruption across positions, which can distort structurally informative tokens. We present BiMol-Diff, a unified diffusion framework for the paired tasks of text-conditioned molecule generation and molecule captioning. Our key component is a token-aware noise schedule that assigns position-dependent corruption based on token recovery difficulty, preserving harder-to-recover substructures during the forward process. On ChEBI-20 and M3-20M, BiMol-Diff improves molecule reconstruction with a 15.4% relative gain in Exact Match and achieves strong captioning results, attaining best BLEU and BERTScore among compared baselines. These results indicate token-aware noising improves fidelity in molecular structure-language modelling.
@article{arxiv.2604.24089,
title = {BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning},
author = {Aditya Hemant Shahane and Anuj Kumar Sirohi and Devansh Arora and Nitin Kumar and Prathosh A P and Sandeep Kumar},
journal= {arXiv preprint arXiv:2604.24089},
year = {2026}
}