Multimodal large language models (MLLMs) have shown promising advancements in
general visual and language understanding. However, the representation of multimodal …

Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match specified
people in infrared images to visible images without annotations, and vice versa. USVI-ReID …

Multi-step multimodal reasoning tasks pose significant challenges for multimodal large
language models (MLLMs), and finding effective ways to enhance their performance in such …

Text embedding has become a foundational technology in natural language processing
(NLP) during the deep learning era, driving advancements across a wide array of …

Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have
made significant advancements in reasoning capabilities. However, they still face …

Despite the rapidly growing demand for multimodal retrieval, progress in this field remains
severely constrained by a lack of training data. In this paper, we introduce MegaPairs, a …

The growing power of large language models (LLMs) has revolutionized how people access
and utilize information. Notably, the LLMs excel at performing fine-grained data …

With the popularity of multimodal techniques, it receives growing interests to acquire useful
information in visual forms. In this work, we formally define an emerging IR paradigm …

Universal Multimodal Retrieval (UMR) aims to enable search across various modalities
using a unified model, where queries and candidates can consist of pure text, images, or a …

The ability of perceiving fine-grained spatial and temporal information is crucial for video-
language retrieval. However, the existing video retrieval benchmarks, such as MSRVTT and …