Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models

arXiv:2404.13013v1 Announce Type: cross
Abstract: We introduce Groma, a Multimodal Large Language Model (MLLM) with grounded and fine-grained visual perception ability. Beyond holistic image understanding, Groma is adept at region-level tasks such as region captioning and visual grounding. Such capabilities are built upon a localized visual tokenization mechanism, where an image input is decomposed into regions of interest and subsequently encoded into region tokens. By integrating region tokens into user instructions and model responses, we seamlessly enable Groma to understand …

arxiv cs.ai cs.cl cs.cv cs.lg language language models large language large language models multimodal tokenization type visual