Molecular representation shapes the balance between target fidelity and exploration in flow based polymer generation
Abstract
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 °C 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.
Related
- MIRRA: Fast, High-Fidelity Molecular Generation with Chemistry-Informed Discrete Flow Matching
- High Fidelity Stochastic Electrode Microstructure Generation for Low Temperature Electrochemical Systems
- Automated transition state generation for mechanistic exploration in organic synthesis
- The Pnictogen Oracle Provider: Multi-Fidelity Graph Landscapes To Benchmark Molecular Optimization
- Programmable Nanozyme Gating: A Molecular Ejector Switch (MES) for High-Fidelity miRNA-21 Sensing
BibTeX
@misc{zhang2026molecular,
title = {{Molecular representation shapes the balance between target fidelity and exploration in flow based polymer generation}},
author = {Tianren Zhang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.16028},
eprint = {2609.16028},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.16028},
}
RIS
TY - UNPB
TI - Molecular representation shapes the balance between target fidelity and exploration in flow based polymer generation
AU - Tianren Zhang
PY - 2026
DA - 2026/09/10
PB - arXiv
DO - 10.48550/arxiv.2609.16028
UR - https://arxiv.org/abs/2609.16028
AB - 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 T_g conditioning, generated property distributions shifted systematically across a 200 °C 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 CO_2/N_2 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.
ER -