# Molecular representation shapes the balance between target fidelity and exploration in flow based polymer generation

arXiv: https://arxiv.org/abs/2609.16028 · HTML: https://mlsanity.com/paper/2609.16028/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 12 of its 50 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 12 of 12)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models](https://mlsanity.com/paper/1811.12823/) (2018)
- [Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discovery](https://mlsanity.com/paper/1803.09518/) (2018)
- [polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics](https://mlsanity.com/paper/2209.14803/) (2022)
- [TransPolymer: a Transformer-based language model for polymer property predictions](https://mlsanity.com/paper/2209.01307/) (2022)
- [Polymer Informatics with Multi-Task Learning](https://mlsanity.com/paper/2010.15166/) (2020)
- [A graph representation of molecular ensembles for polymer property prediction](https://mlsanity.com/paper/2205.08619/) (2022)
- [Polymers for Extreme Conditions Designed Using Syntax-Directed Variational Autoencoders](https://mlsanity.com/paper/2011.02551/) (2020)
- [Inverse Design of Copolymers Including Stoichiometry and Chain Architecture](https://mlsanity.com/paper/2410.02824/) (2024)
- [Multimodal machine learning with large language embedding model for polymer property prediction](https://mlsanity.com/paper/2503.22962/) (2025)
- [Machine learning enables polymer cloud-point engineering via inverse design](https://mlsanity.com/paper/1812.11212/) (2018)

## Abstract (arXiv)

Designing polymers with targeted properties requires navigating vast chemical spaces from limited labeled data. Here we introduce PolyLatentFlow, a framework based on continuous-time flow matching in latent space for unconditional and conditional polymer generation, together with LlamaUni, a multimodal representation combining polymer sequence and 3D structural information. In unconditional generation, PolyLatentFlow with LlamaUni produced the largest yield of valid candidates novel relative to PolyInfo among the evaluated unconditional generators while maintaining high diversity. For Tg conditioning, generated property distributions shifted systematically across a 200 degC target range. In multi-property tasks, molecular representations showed similar surrogate target fidelity but differed markedly in validity, training-set replay, and structural proximity to labeled polymers. PolyLatentFlow with LlamaUni consistently combined high validity with low replay and achieved the largest per-attempt yield of nonreplayed target hits for CO2/N2 conditioning. These results demonstrate latent space flow matching for polymer inverse design and identify molecular representation as a key determinant of target control and exploration beyond labeled chemistry.