Related papers: AVIR: Adaptive Visual In-Document Retrieval for Ef…

Large Vision-Language Models (LVLMs) have become pivotal at the intersection of computer vision and natural language processing. However, the full potential of LVLMs Retrieval-Augmented Generation (RAG) capabilities remains underutilized.…

Visual question answering on document images that contain textual, visual, and layout information, called document VQA, has received much attention recently. Although many datasets have been proposed for developing document VQA systems,…

Abstractive compression utilizes smaller langauge models to condense query-relevant context, reducing computational costs in retrieval-augmented generation (RAG). However,retrieved documents often include information that is either…

The Visual Object Information Retrieval (VOIR) system described in this paper implements an image retrieval approach that combines two layers, the conceptual and the visual layer. It uses terms from a textual thesaurus to represent the…

In this report, we present the winning solution that achieved the 1st place in the Complex Video Reasoning & Robustness Evaluation Challenge 2025. This challenge evaluates the ability to generate accurate natural language answers to…

Visual Document Retrieval (VDR) typically operates as text-to-image retrieval using specialized bi-encoders trained to directly embed document images. We revisit a zero-shot generate-and-encode pipeline: a vision-language model first…

Retrieval-augmented generation (RAG) has emerged to address the knowledge-intensive visual question answering (VQA) task. Current methods mainly employ separate retrieval and generation modules to acquire external knowledge and generate…

Visual document retrieval requires understanding heterogeneous and multi-modal content to satisfy implicit information needs. Recent advances use screenshot-based document encoding with fine-grained late interaction to encode holistic…

Visual-language models (VLMs) excel at data mappings, but real-world document heterogeneity and unstructuredness disrupt the consistency of cross-modal embeddings. Recent late-interaction methods enhance image-text alignment through…

Recent advancements in vision-language models have achieved remarkable results in making language models understand vision inputs. However, a unified approach to align these models across diverse tasks such as image captioning and visual…

Recent advances in test-time optimization have led to remarkable reasoning capabilities in Large Language Models (LLMs), enabling them to solve highly complex problems in math and coding. However, the reasoning capabilities of multimodal…

Understanding and reasoning over long videos pose significant challenges for large video language models (LVLMs) due to the difficulty in processing intensive video tokens beyond context window and retaining long-term sequential…

Current Video Large Language Models (VideoLLMs) suffer from quadratic computational complexity and key-value cache scaling, due to their reliance on processing excessive redundant visual tokens. To address this problem, we propose SharpV, a…

Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding,…

Large Language Models (LLMs) demonstrate impressive ability in handling reasoning tasks. However, unlike humans who can instinctively adapt their problem-solving strategies to the complexity of task, most LLM-based methods adopt a…

In scientific research, the ability to effectively retrieve relevant documents based on complex, multifaceted queries is critical. Existing evaluation datasets for this task are limited, primarily due to the high cost and effort required to…

We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text. Powered by the iterative latent cross-attention of Perceiver, our framework scales with…

Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich visual content (tables, figures, structured layouts) of original document pages. We propose…

Multi-modal large language models (MLLMs) utilizing instruction-following data, such as LLaVA, have achieved great progress in the industry. A major limitation in these models is that visual tokens consume a substantial portion of the…

While user-generated product reviews often contain large quantities of information, their utility in addressing natural language product queries has been limited, with a key challenge being the need to aggregate information from multiple…