LLaVA-OneVision: Easy Visual Task Transfer

We present LLaVA-OneVision, a family of open large multimodal models (LMMs) developed by consolidating our insights into data, models, and visual representations in the LLaVA-NeXT blog series. Our experimental results demonstrate that LLaVA-OneVision is the first single model that can simultaneously push the performance boundaries of open LMMs in three important computer vision scenarios: single-image, multi-image, and video scenarios. Importantly, the design of LLaVA-OneVision allows strong transfer learning across different modalities/scenarios, yielding new emerging capabilities. In particular, strong video understanding and cross-scenario capabilities are demonstrated through task transfer from images to videos.

Authors

• Bo Li vivo Mobile Communication Co., Ltd
• Yuanhan Zhang
• Dong Guo
• Renrui Zhang The Chinese University of Hong Kong
• Feng Li
• Hao Zhang vivo Mobile Communication Co., Ltd
• Kaichen Zhang
• Peiyuan Zhang
• Yanwei Li
• Ziwei Liu City University of Hong Kong
• Chunyuan Li ByteDance Inc.

Keywords

No keywords are indexed for this paper.