JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
By: Kai Liu , Jungang Li , Yuchong Sun and more
Potential Business Impact:
Lets computers understand and create videos with sound.
This paper presents JavisGPT, the first unified multimodal large language model (MLLM) for Joint Audio-Video (JAV) comprehension and generation. JavisGPT adopts a concise encoder-LLM-decoder architecture, featuring a SyncFusion module for spatio-temporal audio-video fusion and synchrony-aware learnable queries to bridge a pretrained JAV-DiT generator. This design enables temporally coherent video-audio understanding and generation from multimodal instructions. We design an effective three-stage training pipeline consisting of multimodal pretraining, audio-video fine-tuning, and large-scale instruction-tuning, to progressively build multimodal comprehension and generation from existing vision-language models. To support this, we further construct JavisInst-Omni, a high-quality instruction dataset with over 200K GPT-4o-curated audio-video-text dialogues that span diverse and multi-level comprehension and generation scenarios. Extensive experiments on JAV comprehension and generation benchmarks show that JavisGPT outperforms existing MLLMs, particularly in complex and temporally synchronized settings.
Similar Papers
JoVA: Unified Multimodal Learning for Joint Video-Audio Generation
CV and Pattern Recognition
Makes videos talk and move realistically.
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
CV and Pattern Recognition
Lets computers talk and see like people.
MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation
CV and Pattern Recognition
Creates talking, moving characters from text.