Related papers: MinerU-Popo: Universal Post-Processing Model for S…

Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data,…

Image-text retrieval, as a fundamental and important branch of information retrieval, has attracted extensive research attentions. The main challenge of this task is cross-modal semantic understanding and matching. Some recent works focus…

Incorporating external knowledge bases in traditional retrieval-augmented generation (RAG) relies on parsing the document, followed by querying a language model with the parsed information via in-context learning. While effective for…

Token pruning has emerged as a mainstream approach for developing efficient Video Large Language Models (Video LLMs). This work revisits and advances the two predominant token-pruning paradigms: attention-based selection and…

Vision-language foundation models, represented by Contrastive Language-Image Pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual tasks. However, existing approaches primarily focus on…

As conference submission volumes continue to grow, accurately recommending suitable reviewers has become a challenge. Most existing methods follow a ``Paper-to-Paper'' matching paradigm, implicitly representing a reviewer by their…

Financial documents--such as 10-Ks, 10-Qs, and investor presentations--span hundreds of pages and combine diverse modalities, including dense narrative text, structured tables, and complex figures. Answering questions over such content…

Artificial intelligence will be one of the key pillars of the next generation of mobile networks (6G), as it is expected to provide novel added-value services and improve network performance. In this context, large language models have the…

Vision-Language Models (VLMs) have shown strong promise on Optical Character Recognition (OCR), yet the sheer number of visual tokens required to encode dense documents incurs prohibitive inference cost. Existing pruning methods rely on…

We aim to develop a retrieval-augmented generation (RAG) framework that answers questions over a corpus of visually-rich documents presented in mixed modalities (e.g., charts, tables) and diverse formats (e.g., PDF, PPTX). In this paper, we…

Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation. However, current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream…

The automated generation of research workflows is essential for improving the reproducibility of research and accelerating the paradigm of "AI for Science". However, existing methods typically extract merely fragmented procedural components…

This technical report introduces Uni-Parser, an industrial-grade document parsing engine tailored for scientific literature and patents, delivering high throughput, robust accuracy, and cost efficiency. Unlike pipeline-based document…

Structured documents--tables paired with captions, figures with explanations, equations with the paragraphs that interpret them--are routinely fragmented when indexed for retrieval. Element-level indexing treats every parsed element as an…

Document dewarping, aiming to eliminate geometric deformation in photographed documents to benefit text recognition, has made great progress in recent years but is still far from being solved. While Cartesian coordinates are typically…

The recent rapid and tremendous success of deep convolutional neural networks (CNN) on many challenging computer vision tasks largely derives from the accessibility of the well-annotated ImageNet and PASCAL VOC datasets. Nevertheless,…

Document extraction is an important step before retrieval-augmented generation (RAG), knowledge bases, and downstream generative AI can work. It turns unstructured documents like PDFs and scans into structured text and layout-aware…

Most organizational data in this world are stored as documents, and visual retrieval plays a crucial role in unlocking the collective intelligence from all these documents. However, existing benchmarks focus on English-only document…

Accurate document parsing requires both robust content recognition and a stable parser interface. In explicit Document Layout Analysis (DLA) pipelines, downstream parsers do not consume the full detector output. Instead, they operate on a…

With recent advances in Multimodal Large Language Models (MLLMs), grounding and referring capabilities have gained increasing attention for achieving detailed understanding and flexible user interaction. However, these capabilities still…