--- license: apache-2.0 library_name: transformers pipeline_tag: image-text-to-text --- This model is **OneSearch-VL-8B**, a unified multimodal deep research agent for single images, multi-image collections, and videos, presented in [OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video](https://huggingface.co/papers/2610.12419). It locates visual clues, retrieves external knowledge, and combines evidence into supported answers. For code and project details, see the [GitHub repository](https://github.com/appletea233/OneSearch-VL).