VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
Nanjing University · Xiamen University · Alibaba Group · Institute of Automation, Chinese Academy of Sciences · Tencent Youtu Lab · University of Illinois at Urbana-Champaign · Tencent · Xiamen University, China · Tencent YouTu Lab · NLPR, CASIA
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
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. However, speech plays a crucial role in multimodal dialogue systems, and implementing high-performance in both vision and speech tasks remains a challenge due to the fundamental modality differences. In this paper, we propose a carefully designed multi-stage training methodology that progressively trains LLM to understand both visual and speech information, ultimately enabling fluent vision and speech interaction. Our approach not only preserves strong vision-language capacity, but also enables efficient speech-to-speech dialogue capabilities without separate ASR and TTS modules, significantly accelerating multimodal end-to-end response speed. By comparing against state-of-the-art counterparts across benchmarks for image, video, and speech, we demonstrate that our omni model is equipped with both strong visual and speech capabilities, making omni understanding and interaction.