VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

NeurIPSSpotlight2025

Authors: Chaoyou Fu, Haojia Lin, Xiong Wang, YiFan Zhang, Yunhang Shen, Xiaoyu Liu, Haoyu Cao, Zuwei Long, Heting Gao, Ke Li, Long MA, Xiawu Zheng, Rongrong Ji, Xing Sun, Caifeng Shan, Ran He
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

large language model language model multimodal speech llm

← All NeurIPS 2025 Spotlight papers · Browse the whole archive