Modality-Inconsistent Continual Learning of Multimodal Large Language Models
This addresses the challenge of maintaining performance in multimodal AI systems when learning new tasks with varying data types, though it appears incremental as it builds on existing continual learning methods.
The paper tackles the problem of catastrophic forgetting in multimodal large language models during continual learning with inconsistent modalities and task types, proposing MoInCL which shows significant improvements over state-of-the-art baselines in experiments across six tasks.
In this paper, we introduce Modality-Inconsistent Continual Learning (MICL), a new continual learning scenario for Multimodal Large Language Models (MLLMs) that involves tasks with inconsistent modalities (image, audio, or video) and varying task types (captioning or question-answering). Unlike existing vision-only or modality-incremental settings, MICL combines modality and task type shifts, both of which drive catastrophic forgetting. To address these challenges, we propose MoInCL, which employs a Pseudo Targets Generation Module to mitigate forgetting caused by task type shifts in previously seen modalities. It also incorporates Instruction-based Knowledge Distillation to preserve the model's ability to handle previously learned modalities when new ones are introduced. We benchmark MICL using a total of six tasks and conduct experiments to validate the effectiveness of our proposed MoInCL. The experimental results highlight the superiority of MoInCL, showing significant improvements over representative and state-of-the-art continual learning baselines.