FLUID: Flow-Latent Unified Integration via Token Distillation for Expert Specialization in Multimodal Learning (2508.07264v1)

Abstract: Multimodal classification requires robust integration of visual and textual signals, yet common fusion strategies are brittle and vulnerable to modality-specific noise. In this paper, we present \textsc{FLUID}-Flow-Latent Unified Integration via Token Distillation for Expert Specialization, a principled token-level pipeline that improves cross-modal robustness and scalability. \textsc{FLUID} contributes three core elements: (1) \emph{Q-transforms}, learnable query tokens that distill and retain salient token-level features from modality-specific backbones; (2) a two-stage fusion scheme that enforces cross-modal consistency via contrastive alignment and then performs adaptive, task-aware fusion through a gating mechanism and a \emph{Q-bottleneck} that selectively compresses information for downstream reasoning; and (3) a lightweight, load-balanced Mixture-of-Experts at prediction time that enables efficient specialization to diverse semantic patterns. Extensive experiments demonstrate that \textsc{FLUID} attains (91\%) accuracy on the GLAMI-1M benchmark, significantly outperforming prior baselines and exhibiting strong resilience to label noise, long-tail class imbalance, and semantic heterogeneity. Targeted ablation studies corroborate both the individual and synergistic benefits of the proposed components, positioning \textsc{FLUID} as a scalable, noise-resilient solution for multimodal product classification.