Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design Article Swipe

MAKE IMPACT

Li, Lingxiao , Zhang Haobo , Chen Bin , Zhou Jiayu · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2511.11894

Text-conditioned molecular generation aims to translate natural-language descriptions into chemical structures, enabling scientists to specify functional groups, scaffolds, and physicochemical constraints without handcrafted rules. Diffusion-based models, particularly latent diffusion models (LDMs), have recently shown promise by performing stochastic search in a continuous latent space that compactly captures molecular semantics. Yet existing methods rely on one-shot conditioning, where the entire prompt is encoded once and applied throughout diffusion, making it hard to satisfy all the requirements in the prompt. We discuss three outstanding challenges of one-shot conditioning generation, including the poor interpretability of the generated components, the failure to generate all substructures, and the overambition in considering all requirements simultaneously. We then propose three principles to address those challenges, motivated by which we propose Chain-of-Generation (CoG), a training-free multi-stage latent diffusion framework. CoG decomposes each prompt into curriculum-ordered semantic segments and progressively incorporates them as intermediate goals, guiding the denoising trajectory toward molecules that satisfy increasingly rich linguistic constraints. To reinforce semantic guidance, we further introduce a post-alignment learning phase that strengthens the correspondence between textual and molecular latent spaces. Extensive experiments on benchmark and real-world tasks demonstrate that CoG yields higher semantic alignment, diversity, and controllability than one-shot baselines, producing molecules that more faithfully reflect complex, compositional prompts while offering transparent insight into the generation process.

Type

preprint

Landing Page

https://doi.org/10.48550/arxiv.2511.11894

OA Status

green

OpenAlex ID

https://openalex.org/W7105981584

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W7105981584

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2511.11894

Digital Object Identifier

Title

Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design

Work title

Type

preprint

OpenAlex work type

Publication year

2025

Year of publication

Publication date

2025-11-14

Full publication date if available

Authors

Li, Lingxiao, Zhang Haobo, Chen Bin, Zhou Jiayu

List of authors in order

Landing page

https://doi.org/10.48550/arxiv.2511.11894

Publisher landing page

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://doi.org/10.48550/arxiv.2511.11894

Direct OA link when available

Concepts

Computer science, Interpretability, Benchmark (surveying), Artificial intelligence, Controllability, Semantics (computer science), Syntax, Theoretical computer science, Space (punctuation), Trajectory, Markov chain, GRASP, Dimensionality reduction, Machine learning, Word (group theory), Argument (complex analysis), Function (biology), Markov process, Perspective (graphical), Latent variable, Diffusion, Feature (linguistics), Dependency (UML)

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Full payload