AI Paper Atlas

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

Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling

Divyam Madaan, Sumit Chopra, Kyunghyun Cho

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 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
include the time-series modality in MIMIC-III mortality predictionunimodal baseline · MIMIC-III mortalityaccuracy (%): 76.36 -> 77.89Improved
add the time-series modality for respiratory ICD-9 460-519 predictionunimodal baseline · MIMIC-III ICD-9 460-519accuracy (%): 56.22 -> 68.22Improved
add the time-series modality for neoplasm ICD-9 140-239 predictionunimodal baseline · MIMIC-III ICD-9 140-239accuracy (%): 91.42 -> 91.37No clear effect
add the audio modality on AV-MNISTunimodal vision baseline · AV-MNISTaccuracy (%): 40.36 -> 71.32Improved
PRIMO latent completion with complete modalities versus the multimodal baselinePRIMO · AV-MNISTaccuracy (%): 71.14 -> 68.17 (audio), 71.32 -> 68.27 (vision)Hurt
use PRIMO versus MVAE and MMVAE with complete inputs on XORmissing-modality models · Synthetic XORaccuracyImproved

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