analiza aiqbench
MM-Spectrum addresses the challenge of integrating heterogeneous spectroscopic signals for molecular structure elucidation using a sparse Mixture-of-Experts framework. By introducing modality-aware routing and specialized expert architectures, it effectively mitigates performance degradation caused by multimodal imbalance and noise interference. This approach demonstrates substantial improvements across various data settings, offering a robust solution for complex scientific inference tasks in computational chemistry.
MM-Spectrum: Multimodal Multi-spectral Molecular Structural Elucidation with a Stable MoE Framework
arXiv:2608.27286v1 Announce Type: new Abstract: Inferring molecular structures from multimodal spectroscopic measurements requires integrating complementary yet highly heterogeneous signals. However, the common paradigm of directly concatenating multispectral sequences can exhibit anomalous performance degradation, primarily due to pronounced heterogeneity and the resulting multimodal imbalance across modalities. As a remedy, we propose MM-Spectrum, a sparse Mixture-of-Experts framework tailored for multimodal multispectral spectra-to-structure elucidation. To better match the information characteristics under multispectral imbalance, MM-Spectrum introduces an explicit modality-aware routing mechanism that exposes spectral identity to the router in addition to token content representations. Moreover, it incorporates shared and interaction experts, together with heterogeneous expert capacities, to extract multispectral modality-unique and cross-modal synergistic information while suppressing noise-induced interference. Across full-modality, bimodal, and missing-modality settings on molecular structural elucidation, MM-Spectrum achieves consistent and substantial improvements, supported by ablation studies and interpretability analyses.
Abstract:Inferring molecular structures from multimodal spectroscopic measurements requires integrating complementary yet highly heterogeneous signals. However, the common paradigm of directly concatenating multispectral sequences can exhibit anomalous performance degradation, primarily due to pronounced heterogeneity and the resulting multimodal imbalance across modalities. As a remedy, we propose MM-Spectrum, a sparse Mixture-of-Experts framework tailored for multimodal multispectral spectra-to-structure elucidation. To better match the information characteristics under multispectral imbalance, MM-Spectrum introduces an explicit modality-aware routing mechanism that exposes spectral identity to the router in addition to token content representations. Moreover, it incorporates shared and interaction experts, together with heterogeneous expert capacities, to extract multispectral modality-unique and cross-modal synergistic information while suppressing noise-induced interference. Across full-modality, bimodal, and missing-modality settings on molecular structural elucidation, MM-Spectrum achieves consistent and substantial improvements, supported by ablation studies and interpretability analyses.
Machine Learning (cs.LG)
arXiv:2608.27286 [cs.LG]
(or arXiv:2608.27286v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.27286 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 226 cuvinte
Subiecte conexe
Hypothesis-and-Refinement Learning of Organic Structures from Multimodal Spectroscopic Data
arXiv · 23 iul. 2026
Towards Reasonable Molecular Structure Elucidation from Infrared Spectroscopy with Chemical Feedback
arXiv · 19 aug. 2026
Explainable Molecular Structure Inference from GC--MS with Diffusion Models and LLM Reranking
arXiv · 5 oct. 2026
MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation
arXiv · 10 oct. 2026