arXiv Machine Learning June 15, 2026 By Xi Wang, Jiahan Li, Yuxuan Xia, Yingcheng Wu, Shaoyi Zheng, Shengjie Wang

Smoothing Dark Areas in Molecular Latent Diffusion

Read the original on arXiv Machine Learning →

arXiv:2606. 13955v1 Announce Type: new Abstract: Latent diffusion is a promising framework for scalable 3D molecular generation, but it requires a latent space that remains smooth, valid, and navigable beyond posterior samples.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

diffusion

arXiv Machine Learning

Jul 13

Autoregressive latent diffusion for 3D molecule generation

arXiv:2607. 09277v1 Announce Type: new Abstract: Three-dimensional (3D) molecule generation has been dominated by diffusion models, which achieve strong generation quality but typically require the molecular size to be specified a priori.

By Federico Ottomano, Gaopeng Ren, Yingzhen Li, Kim E. Jelfs, Alex M. Ganose

diffusion

arXiv Machine Learning

Jun 2

Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation

arXiv:2606. 01595v1 Announce Type: new Abstract: Bayesian inference provides a principled framework for modeling epistemic uncertainty in neural networks by treating predictions as distributions rather than deterministic values.

By Fang Wan, Jingxiang Qu, Yi Liu

diffusion benchmarks

arXiv Machine Learning

Jul 8

Multimodal Molecular Representation Learning with Graph Neural Networks, Deep & Cross Networks, and SMILES Embeddings

arXiv:2607. 05736v1 Announce Type: new Abstract: Molecular property prediction often relies on isolated data modalities, where continuous 3D graph neural networks (GNNs) struggle to efficiently capture long-range topological dependencies and exact macroscopic heuristics.

By Qiwei Han, Chi Zhou, Ruobing Wang, Zheng Ma

rag diffusion efficiency multimodal benchmarks safety

arXiv Machine Learning

Aug 13

NAE: Normalizing AutoEncoder

arXiv:2608. 12084v1 Announce Type: new Abstract: We consider the setting of Normalizing flows with approximate inverses, an established paradigm spanning both full-dimensional ($d=D$) and bottleneck ($d<D$) settings, and group these models under the term flow autoencoders.

By Muhammad Abdur Rafae, Niels Landwehr

benchmarks safety

arXiv Machine Learning

Aug 17

Conditional Neural Optimal Transport for Predicting Cellular Phenotypes from Molecular Structure

arXiv:2608. 14293v1 Announce Type: cross Abstract: High-content microscopy enables systematic profiling of cellular responses to chemical perturbations, but the scale of the chemical space makes exhaustive phenotypic characterization experimentally infeasible.

By Gauthier Avit\'e, Maxime Sanchez-Renauld, Nicolas Bourriez, Auguste Genovesio

arXiv AI

Aug 7

Domain-Gated Latent Diffusion: Generative Inverse Design of HMX-Class Energetic Materials with First-Principles Validation

arXiv:2605. 26540v2 Announce Type: replace-cross Abstract: Energetic materials power mining, demolition, propulsion and airbags, yet today's compounds were designed decades ago.

By Yehudit Aperstein, Alexander Apartsin

diffusion benchmarks safety

One email a morning, machine-written

Related stories

Autoregressive latent diffusion for 3D molecule generation

Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation

Multimodal Molecular Representation Learning with Graph Neural Networks, Deep & Cross Networks, and SMILES Embeddings

NAE: Normalizing AutoEncoder

Conditional Neural Optimal Transport for Predicting Cellular Phenotypes from Molecular Structure

Domain-Gated Latent Diffusion: Generative Inverse Design of HMX-Class Energetic Materials with First-Principles Validation