SOURCE-LINKED INTELLIGENCE

NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Experts

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Multimodal continual learning has recently shown great potential for developing agents with human-like intelligence by continuously learning new tasks across multiple modalities. However, existing methods typically assume that the set of modalities per task is predefined and fixed. In this paper, we investigate a more realistic learning setting, referred to as dynamic multimodal continual learning, in which the set of modalities may vary across tasks rather than remaining fixed. This setting involves two primary challenges: (i) spatio-temporal catastrophic forgetting and (ii) adaptive multimod

Read original source ↗ Open in workspace

recordType

paper

region

Global