# Robust Multimodal Learning via Entropy-Gated Contrastive Fusion

Source: [Robust Multimodal Learning via Entropy-Gated Contrastive Fusion](<https://www.sota2.com/research/paper/68fa78b91e209131cea7a0c0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:45:08.569Z

Authors: Leon Chlon, Maggie Chlon, MarcAntonio M. Awada

Published: 2025-05-21T12:00:37.000Z

## Abstract

Real-world multimodal systems routinely face missing-input scenarios, and in reality, robots lose audio in a factory or a clinical record omits lab tests at inference time. Standard fusion layers either preserve robustness or calibration but never both. We introduce Adaptive Entropy-Gated Contrastive Fusion (AECF), a single light-weight layer that (i) adapts its entropy coefficient per instance, (ii) enforces monotone calibration across all modality subsets, and (iii) drives a curriculum mask directly from training-time entropy. On AV-MNIST and MS-COCO, AECF improves masked-input mAP by +18 pp at a 50% drop rate while reducing ECE by up to 200%, yet adds 1% run-time. All back-bones remain frozen, making AECF an easy drop-in layer for robust, calibrated multimodal inference.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.15417>)

[PDF](<https://arxiv.org/pdf/2505.15417.pdf>)