3 accepted papers
"We present , a versatile multi-modal large language model (MLLM) with a joint mixing of model weights, visual embeddings and image scales. First, for stronger vision-language alignment, we unfreeze the large language model (LLM) during pre-training, and introduce a weight mix strategy between LLMs…
We introduce CogVLM, a powerful open-source visual language foundation model. Different from the popular \emph{shallow alignment} method which maps image features into the input space of language model, CogVLM bridges the gap between the frozen pretrained language model and image encoder by a traina…
Weakly supervised phrase grounding aims to learn an alignment between phrases in a caption and objects in a corresponding image using only caption-image annotations, i.e., without phrase-object annotations. Previous methods typically use a caption-image contrastive loss to indirectly supervise the a…