2024/02/12 by Yun-Da Tsai, Tsai, Yun-Da, Ting‐Yu Yen +7 · 1 citation
Computer Science · #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques
paper · pdf · doi:10.48550/arxiv.2402.08086
openalex publication_date 2024/02/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This research paper addresses the challenge of modality mismatch in multimodal learning, where the modalities available during inference differ from those available at training. We propose the Text-centric Alignment for Multi-Modality Learning (TAMML) approach, an innovative method that utilizes Large Language Models (LLMs) with in-context learning and foundation models to enhance the generalizability of multimodal systems under these conditions. By leveraging the unique properties of text as a unified semantic space, TAMML demonstrates significant improvements in handling unseen, diverse, and unpredictable modality combinations. TAMML not only adapts to varying modalities but also maintains robust performance, showcasing the potential of foundation models in overcoming the limitations of traditional fixed-modality frameworks in embedding representations. This study contributes to the field by offering a flexible, effective solution for real-world applications where modality availability is dynamic and uncertain.