Related papers: NanoVDR: Distilling a 2B Vision-Language Retriever…

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…

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…

Visual encoders are fundamental components in vision-language models (VLMs), each showcasing unique strengths derived from various pre-trained visual foundation models. To leverage the various capabilities of these encoders, recent studies…

Visual Document Retrieval (VDR) requires representations that capture both fine-grained visual details and global document structure to ensure retrieval efficacy while maintaining computational efficiency. Existing VDR models struggle to…

Vision-Language Models (VLMs) excel in diverse visual tasks but face challenges in document understanding, which requires fine-grained text processing. While typical visual tasks perform well with low-resolution inputs, reading-intensive…

In this report, we propose PaddleOCR-VL, a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic…

Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks. However, popular VLMs usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and…

Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resolution input to boost model performance, this often leads to…

Disentangled representation learning remains challenging as the underlying factors of variation in the data do not naturally exist. The inherent complexity of real-world data makes it unfeasible to exhaustively enumerate and encapsulate all…

Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the…

Visual Document Retrieval (VDR), the task of retrieving visually-rich document pages using queries that combine visual and textual cues, is crucial for numerous real-world applications. Recent state-of-the-art methods leverage Large…

Large Language Models (LLMs)-based text retrieval retrieves documents relevant to search queries based on vector similarities. Documents are pre-encoded offline, while queries arrive in real-time, necessitating an efficient online query…

Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts…

Almost all previous text-to-video retrieval works ideally assume that videos are pre-trimmed with short durations containing solely text-related content. However, in practice, videos are typically untrimmed in long durations with much more…

Understanding visually situated language requires interpreting complex layouts of textual and visual elements. Pre-processing tools, such as optical character recognition (OCR), can map document image inputs to textual tokens, then large…

Vision-Language Models (VLMs) have shown remarkable performance on diverse visual and linguistic tasks, yet they remain fundamentally limited in their understanding of 3D spatial structures. We propose Geometric Distillation, a lightweight,…

Vision-and-language models (VLMs) have been increasingly explored in the medical domain, particularly following the success of CLIP in general domain. However, unlike the relatively straightforward pairing of 2D images and text, curating…

Cross-model retrieval has emerged as one of the most important upgrades for text-only search engines (SE). Recently, with powerful representation for pairwise text-image inputs via early interaction, the accuracy of vision-language (VL)…

Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current multimodal retrieval applications. The state-of-the-art multi-vector paradigm excels in…

For visual recognition, knowledge distillation typically involves transferring knowledge from a large, well-trained teacher model to a smaller student model. In this paper, we introduce an effective method to distill knowledge from an…