Score: 0

JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation

Published: December 28, 2025 | arXiv ID: 2512.22905v1

By: Kai Liu , Jungang Li , Yuchong Sun and more

Potential Business Impact:

Lets computers understand and create videos with sound.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

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.

Country of Origin
🇨🇳 China

Page Count
29 pages

Category
Computer Science:
CV and Pattern Recognition