雪貂：在任何粒度的任何地方引用和研磨任何东西论文（英文版）

Ferret enables referring and grounding capabilities for multimodal large language model (LLM). In terms of referring, a user can refer to a region or an object in point, box, or any free-form shape. The regionN in the input will be replaced by the proposed hybrid representation before being fed into the LLM. In terms of grounding, Ferret is able to accurately ground any open-vocabulary descriptions. The boxN in the output denotes the predicted bounding box coordinates.