相关论文: MURE: Hierarchical Multi-Resolution Encoding via V…

Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce…

Visually Rich Document Understanding (VRDU) has become a pivotal area of research, driven by the need to automatically interpret documents that contain intricate visual, textual, and structural elements. Recently, Multimodal Large Language…

This paper presents Universal Vision-Language Dense Retrieval (UniVL-DR), which builds a unified model for multi-modal retrieval. UniVL-DR encodes queries and multi-modality resources in an embedding space for searching candidates from…

Large Vision-Language Models (LVLMs) usually suffer from prohibitive computational and memory costs due to the quadratic growth of visual tokens with image resolution. Existing token compression methods, while varied, often lack a…

Mixture of Vision Encoders (MoVE) has emerged as a powerful approach to enhance the fine-grained visual understanding of multimodal large language models (MLLMs), improving their ability to handle tasks such as complex optical character…

Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various feature aggregation methods to transform deep features into…

We introduce MUSE-VL, a Unified Vision-Language Model through Semantic discrete Encoding for multimodal understanding and generation. Recently, the research community has begun exploring unified models for visual generation and…

Recent breakthroughs in Visual Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have significantly advanced 3D scene perception towards language-driven cognition. However, existing 3D language models struggle with sparse,…

The rise of multi-modal search requests from users has highlighted the importance of multi-modal retrieval (i.e. image-to-text or text-to-image retrieval), yet the more complex task of image-to-multi-modal retrieval, crucial for many…

Text-to-image retrieval (T2I retrieval) remains challenging because cross-modal embeddings often behave as bags of concepts, underrepresenting structured visual relationships such as pose and viewpoint. We proposeVisualize-then-Retrieve…

Understanding visually-rich business documents to extract structured data and automate business workflows has been receiving attention both in academia and industry. Although recent multi-modal language models have achieved impressive…

Documents are visually rich structures that convey information through text, but also figures, page layouts, tables, or even fonts. Since modern retrieval systems mainly rely on the textual information they extract from document pages to…

Harnessing the full potential of visually-rich documents requires retrieval systems that understand not just text, but intricate layouts, a core challenge in Visual Document Retrieval (VDR). The prevailing multi-vector architectures, while…

This work introduces VERSE, a methodology for analyzing and improving Vision-Language Models applied to Visually-rich Document Understanding by exploring their visual embedding space. VERSE enables the visualization of latent…

Retrieving specific information from a large corpus of documents is a prevalent industrial use case of modern AI, notably due to the popularity of Retrieval-Augmented Generation (RAG) systems. Although neural document retrieval models have…

This paper proposes Multi-modAl Retrieval model via Visual modulE pLugin (MARVEL), which learns an embedding space for queries and multi-modal documents to conduct retrieval. MARVEL encodes queries and multi-modal documents with a unified…

Retrieval-Augmented Generation (RAG) has become a core paradigm in document question answering tasks. However, existing methods have limitations when dealing with multimodal documents: one category of methods relies on layout analysis and…

Visual token pruning aims to compress and prune redundant visual tokens which play a critical role in efficient inference with large vision-language models (LVLMs). However, most existing work estimates visual redundancy using a single…

Current vision-language models (VLMs) still exhibit inferior performance on knowledge-intensive tasks, primarily due to the challenge of accurately encoding all the associations between visual objects and scenes to their corresponding…

Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vector representations in information retrieval applications. In multi-vector retrieval systems, both…