Dongxing Yu, Sanda University, China

Recent advancements in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in processing diverse data types, yet significant disparities persist between human cognitive processes and computational approaches to multimodal information integration. This research presents a systematic investigation into the parallels between human cross-modal chunking mechanisms and token representation methodologies in MLLMs. Through empirical studies comparing human performance patterns with model behaviors across visual-linguistic tasks, we demonstrate that conventional static tokenization schemes fundamentally constrain current models' capacity to simulate the dynamic, context-sensitive nature of human information processing. We propose a novel framework for dynamic cross-modal tokenization that incorporates adaptive boundaries, hierarchical representations, and alignment mechanisms grounded in cognitive science principles. Quantitative evaluations demonstrate that our approach yields statistically significant improvements over state-of-the-art models on benchmark tasks (+7.8% on Visual Question Answering, +5.3% on Complex Scene Description) while exhibiting more human-aligned error patterns and attention distributions. These findings contribute to the theoretical understanding of the relationship between human cognition and artificial intelligence, while providing empirical evidence for developing more cognitively plausible AI systems.

Multimodal language models, tokenization, cognitive chunking, cross-modal integration, hierarchical representations, adaptive processing, visual-linguistic understanding, transfer learning, human-aligned AI, neural information processing