AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

MM-Spectrum: Multimodal Multi-spectral Molecular Structural Elucidation with a Stable MoE Framework

Hai-tao Yu, Min Nan, Zheng Fang, Hongyu Zhan, Yusen Tan, Yuhan Wang, Jun Xia

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Router-aware signals (ablation)MM-Spectrum · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 72.57 -> 76.04Improved
add Tag routing (ablation)MM-Spectrum · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 71.23 -> 76.04Improved
add both Router-aware signals and Tag routing (ablation)MM-Spectrum · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 70.11 -> 76.04Improved
add Dynamic activation (ablation)MM-Spectrum · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 74.41 -> 76.04Improved
add Interaction experts (ablation)MM-Spectrum · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 74.39 -> 76.04Improved
add Shared experts (ablation)MM-Spectrum · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 75.01 -> 76.04Improved
add computation-aware regularizer (ablation)MM-Spectrum · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 74.81 -> 76.04Improved
add heterogeneous expert capacities (ablation)MM-Spectrum · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 74.07 -> 76.04Improved
add heterogeneous capacities without regularizer vs neither (ablation)MM-Spectrum · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 74.24 vs 74.07No clear effect
replace dense concatenation with modality-aware sparse MoEDense concatenation · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 44.29 -> 76.04Improved
add IR and MS to NMR with dense concatenationDense concatenation · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 69.83 -> 44.29Hurt
use Gradient Blending instead of plain dense concatenationDense concatenation · Spectra benchmark (NMR+MS+IR)Top-1 accuracy: 44.29 -> 46.78Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy