Unlocking Pretrained LLMs for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction

Shinichi Tanaka, Zhao Wang, Yoichi Kato +1

In this paper, we propose a unified framework that leverages a single pretrained LLM for Motion-related Multimodal Generation, referred to as MoMug. MoMug integrates diffusion-base…