相关论文: DocRetriever: A Plug-and-Play Framework for Multim…

Recently, automatically extracting information from visually rich documents (e.g., tickets and resumes) has become a hot and vital research topic due to its widespread commercial value. Most existing methods divide this task into two…

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…

Fine-grained medical image classification is challenged by subtle inter-class variations and visually ambiguous cases, where confidence estimates often exhibit uncertainty rather than being overconfident. In such scenarios, purely…

Multimedia retrieval plays an indispensable role in big data utilization. Past efforts mainly focused on single-media retrieval. However, the requirements of users are highly flexible, such as retrieving the relevant audio clips with one…

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely…

In a retrieval system, simultaneously achieving search accuracy and efficiency is inherently challenging. This challenge is particularly pronounced in partially relevant video retrieval (PRVR), where incorporating more diverse context…

Legal precedent retrieval is a cornerstone of the common law system, governed by the principle of stare decisis, which demands consistency in judicial decisions. However, the growing complexity and volume of legal documents challenge…

With the rapid advancement of multimodal retrieval and its application in LLMs and multimodal LLMs, increasingly complex retrieval tasks have emerged. Existing methods predominantly rely on task-specific fine-tuning of vision-language…

Multi-hop question answering (MHQA) involves reasoning across multiple documents to answer complex questions. Dense retrievers typically outperform sparse methods like BM25 by leveraging semantic embeddings; however, they require labeled…

Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets. However, previous studies have found that dense retrieval is hard to generalize to unseen domains due to its weak modeling of…

Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Prior work usually focuses on the pairwise relations (i.e., whether a data sample matches another) but ignores the…

Large vision-language models increasingly rely on long-context modeling to reason over documents, hour-level videos, and long-horizon agent trajectories, requiring them to locate relevant evidence across interleaved text and images. Prior…

Deep Research Agents (DRAs) generate citation-rich reports via multi-step search and synthesis, yet existing benchmarks mainly target text-only settings or short-form multimodal QA, missing end-to-end multimodal evidence use. We introduce…

Layout is a fundamental component of any graphic design. Creating large varieties of plausible document layouts can be a tedious task, requiring numerous constraints to be satisfied, including local ones relating different semantic elements…

Academic peer review remains the cornerstone of scholarly validation, yet the field faces some challenges in data and methods. From the data perspective, existing research is hindered by the scarcity of large-scale, verified benchmarks and…

Open-domain extractive question answering works well on textual data by first retrieving candidate texts and then extracting the answer from those candidates. However, some questions cannot be answered by text alone but require information…

Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for retrieval at each reasoning step, limiting information…

Retrieval over visually rich documents is essential for tasks such as legal discovery, scientific search, and enterprise knowledge management. Existing approaches fall into two paradigms: single-vector retrieval, which is efficient but…

In this paper, we introduce ReasonEmbed, a novel text embedding model developed for reasoning-intensive document retrieval. Our work includes three key technical contributions. First, we propose ReMixer, a new data synthesis method that…

Existing information retrieval (IR) models often assume a homogeneous format, limiting their applicability to diverse user needs, such as searching for images with text descriptions, searching for a news article with a headline image, or…