# BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning

arXiv: https://arxiv.org/abs/2604.24089 · HTML: https://mlsanity.com/paper/2604.24089/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models](https://mlsanity.com/paper/2210.08933/) (2022)
- [Translation between Molecules and Natural Language](https://mlsanity.com/paper/2204.11817/) (2022)
- [MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter](https://mlsanity.com/paper/2310.12798/) (2023)
- [Unifying Molecular and Textual Representations via Multi-task Language Modelling](https://mlsanity.com/paper/2301.12586/) (2023)
- [GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text](https://mlsanity.com/paper/2308.06911/) (2023)
- [MolXPT: Wrapping Molecules with Text for Generative Pre-training](https://mlsanity.com/paper/2305.10688/) (2023)
- [Structure-informed Language Models Are Protein Designers](https://mlsanity.com/paper/2302.01649/) (2023)
- [Graph Diffusion Transformers for Multi-Conditional Molecular Generation](https://mlsanity.com/paper/2401.13858/) (2024)
- [Text-Guided Molecule Generation with Diffusion Language Model](https://mlsanity.com/paper/2402.13040/) (2024)
- [UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation](https://mlsanity.com/paper/2408.00863/) (2024)
- [LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models](https://mlsanity.com/paper/2405.17829/) (2024)
- [3M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation](https://mlsanity.com/paper/2403.07179/) (2024)
- [Interactive Molecular Discovery with Natural Language](https://mlsanity.com/paper/2306.11976/) (2023)
- [Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model](https://mlsanity.com/paper/2408.09896/) (2024)
- [GraphT5: Unified Molecular Graph-Language Modeling via Multi-Modal Cross-Token Attention](https://mlsanity.com/paper/2503.07655/) (2025)
- [Training Text-to-Molecule Models with Context-Aware Tokenization](https://mlsanity.com/paper/2509.04476/) (2025)

## Abstract (arXiv)

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.