arXiv Machine Learning August 28, 2026 By Mary Ogbuka Kenneth, Foaad Khosmood, Abbas Edalat

Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusion

Read the original on arXiv Machine Learning →

The paper introduces Inverted Asymmetric Fusion (IAF) to address strong-modality collapse in multimodal learning, where dominant modalities are degraded during fusion. IAF preserves the dominant modality by passing it unchanged and letting weaker modalities attend to it, while also strengthening weaker modalities via Modality-Aware Knowledge Distillation. Experiments on MultiHuSE, UR-FUNNY, and MUStARD show that IAF maintains unimodal performance and improves over the best unimodal baseline by up to 8.25%.

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.

arXiv Machine Learning

Jun 2

Feature Alignment Determines Fusion Strategy: A Comparative Study of Cross-Attention and Concatenation in Multimodal Learning

arXiv:2606. 01207v1 Announce Type: cross Abstract: The choice between cross-attention and concatenation for multimodal fusion remains governed by practitioner intuition rather than principled understanding.

By Zhiqiang Zhou, Xuezhen Xie

llms multimodal safety

arXiv AI

Jun 3

CL-DMDF:Dynamic Multimodal Data Fusion Model Based on Contrastive Learning

arXiv:2606. 02659v1 Announce Type: cross Abstract: Multimodal data fusion involves integrating and analyzing information from multiple modalities to uncover latent correlations and complementary patterns, thereby enhancing data processing and decision-making.

By Dong Li, Lingling Zhang, Binghao Han, Linlin Ding, Yue Kou

multimodal

arXiv Machine Learning

Jun 3

Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals

arXiv:2606. 02679v1 Announce Type: new Abstract: Multimodal systems often benefit from combining information across language, sound, and visual streams, but this benefit is not guaranteed.

By Jiyuan Liu, Liangwei Nathan Zheng, Wei Emma Zhang, Xinpei Wang, Weitong Chen

multimodal benchmarks

arXiv Machine Learning

Jul 7

Beyond Modality Fusion: Deep Ensembles for Multimodal Classification

arXiv:2607. 05019v1 Announce Type: new Abstract: In multimodal classification, late-fusion approaches classify concatenated modality-specific features extracted by unimodal neural networks.

By Ilya Burenko, Dmitry Vetrov

multimodal benchmarks

arXiv Machine Learning

Jun 10

SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning

arXiv:2606. 09853v1 Announce Type: new Abstract: A central objective in multimodal learning is to capture synergy: task-relevant information that arises only from the joint use of multiple modalities, and is not available from any single modality alone.

By Konstantinos Kontras, Teodora Gagaleska, Thomas Strypsteen, Christos Chatzichristos, Matthew Blaschko, Maarten De Vos, Paul Pu Liang

multimodal benchmarks

arXiv AI

Jun 2

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition

arXiv:2606. 00959v1 Announce Type: new Abstract: Understanding modality interaction in multimodal large language models (MLLMs) is central to reliable deployment.

By Wanlong Fang, Tianle Zhang, Wen Tao, Alvin Chan

llms multimodal benchmarks safety

One email a morning, machine-written

Related stories

Feature Alignment Determines Fusion Strategy: A Comparative Study of Cross-Attention and Concatenation in Multimodal Learning

CL-DMDF:Dynamic Multimodal Data Fusion Model Based on Contrastive Learning

Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals

Beyond Modality Fusion: Deep Ensembles for Multimodal Classification

SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition