With the exponential surge in diverse multimodal data, traditional unimodal retrieval
methods struggle to meet the needs of users seeking access to data across various …

Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities
in executing instructions for a variety of single-image tasks. Despite this progress, significant …

Abstract We introduce AutoVER, an Autoregressive model for Visual Entity Recognition. Our
model extends an autoregressive Multimodal Large Language Model by employing retrieval …

Knowledge-based Visual Question Answering (KVQA) tasks require answering questions
about images using extensive background knowledge. Despite significant advancements …

Despite the astonishing performance of recent Large Vision-Language Models (LVLMs),
these models often generate inaccurate responses. To address this issue, previous studies …

CLIP is a powerful and widely used tool for understanding images in the context of natural
language descriptions to perform nuanced tasks. However, it does not offer application …

While large pre-trained visual-language models have shown promising results on traditional
visual question answering benchmarks, it is still challenging for them to answer complex …

The late interaction paradigm introduced with ColBERT stands out in the neural Information
Retrieval space, offering a compelling effectiveness-efficiency trade-off across many …

Visual question answering (VQA) tasks, often performed by visual language model (VLM),
face challenges with long-tail knowledge. Recent retrieval-augmented VQA (RA-VQA) …

With the breakthrough of multi-modal large language models (MLLMs), answering complex
visual questions that demand advanced reasoning abilities and world knowledge has …