Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey
It provides a framework for researchers working on multimodal AI, but it is incremental as it builds on existing NTP methods.
This survey tackles the problem of unifying multimodal learning tasks by proposing a comprehensive taxonomy based on Next Token Prediction (NTP), covering aspects like tokenization, model architectures, and datasets to aid researchers in exploring multimodal intelligence.
Building on the foundations of language modeling in natural language processing, Next Token Prediction (NTP) has evolved into a versatile training objective for machine learning tasks across various modalities, achieving considerable success. As Large Language Models (LLMs) have advanced to unify understanding and generation tasks within the textual modality, recent research has shown that tasks from different modalities can also be effectively encapsulated within the NTP framework, transforming the multimodal information into tokens and predict the next one given the context. This survey introduces a comprehensive taxonomy that unifies both understanding and generation within multimodal learning through the lens of NTP. The proposed taxonomy covers five key aspects: Multimodal tokenization, MMNTP model architectures, unified task representation, datasets \& evaluation, and open challenges. This new taxonomy aims to aid researchers in their exploration of multimodal intelligence. An associated GitHub repository collecting the latest papers and repos is available at https://github.com/LMM101/Awesome-Multimodal-Next-Token-Prediction