Class-Conditional Autoencoders with Adversarial Alignment for Multimodal Fusion
Its authors withdrew this paper, so there is no full text to read or summarize.
Lists
Only you see this
Abstract
Large-scale multimodal transformers excel at cross-modal reasoning but incur prohibitive computational costs and lack theoretical grounding. We propose **DEF+AAF**, combining *Discriminative Embedding (DEF)* with *Adversarial Alignment (AAF)* to achieve provably robust multimodal fusion. We prove that class-conditional variance contraction + Wasserstein barycenter alignment provides a tighter generalization bound (**Theorem 3**) than standard contrastive methods, reducing expected error by $O(\sqrt{M/N})$ where $M$ is modality count. On emotion recognition (IEMOCAP, MOSEI) and translation (Multi30k, How2), DEF+AAF matches transformer baselines at 2.4× fewer parameters and 1.6× lower FLOPs, with +8.4% robustness gain under 50% missing modalities.
BibTeX
@misc{han2026class,
author = {Zhang Han and Xingwen Zhao and Hui Li},
title = {{Class-Conditional Autoencoders with Adversarial Alignment for Multimodal Fusion}},
year = {2026},
url = {https://openreview.net/forum?id=Qq4dF7Zorb},
howpublished = {OpenReview},
note = {Submitted to ICLR 2026},
}Loading related content...