Recent advances in large language models (LLMs) have demonstrated significant promise in document understanding and questionanswering.Despite the progress, existing approaches can only process short documents due to limited context length or fail to fully leverage multi-modal information.In this work, we introduce DocAgent, a multi-agent framework for long-context document understanding that imitates the human reading practice.Specifically, we first extract a structured, tree-formatted outline from documents to help agents identify relevant sections efficiently.Further, we develop an interactive reading interface that enables agents to query and retrieve various types of content dynamically.To ensure answer reliability, we introduce a reviewer agent that cross-checks responses using complementary sources and maintains a task-agnostic memory bank to facilitate knowledge sharing across tasks.We evaluate our method on two long-context document understanding benchmarks, where it bridges the gap to human-level performance by surpassing competitive baselines, while maintaining a short context length.Our code is available at https://github.com/lisun-ai/DocAgent.

This paper introduces an innovative methodology for producing high-quality 3D lung CT images guided by textual information. While diffusion-based generative models are increasingly used in medical imaging, current state-of-the-art approaches are limited to low-resolution outputs and underutilize radiology reports' abundant information. The radiology reports can enhance the generation process by providing additional guidance and offering fine-grained control over the synthesis of images. Nevertheless, expanding text-guided generation to high-resolution 3D images poses significant memory and anatomical detail-preserving challenges. Addressing the memory issue, we introduce a hierarchical scheme that uses a modified UNet architecture. We start by synthesizing low-resolution images conditioned on the text, serving as a foundation for subsequent generators for complete volumetric data. To ensure the anatomical plausibility of the generated samples, we provide further guidance by generating vascular, airway, and lobular segmentation masks in conjunction with the CT images. The model demonstrates the capability to use textual input and segmentation tasks to generate synthesized images. Algorithmic comparative assessments and blind evaluations conducted by 10 board-certified radiologists indicate that our approach exhibits superior performance compared to the most advanced models based on GAN and diffusion techniques, especially in accurately retaining crucial anatomical features such as fissure lines and airways. This innovation introduces novel possibilities. This study focuses on two main objectives: (1) the development of a method for creating images based on textual prompts and anatomical components, and (2) the capability to generate new images conditioning on anatomical elements. The advancements in image generation can be applied to enhance numerous downstream tasks.

Toward the development of effective and efficient brain-computer interface (BCI) systems, precise decoding of brain activity measured by an electroencephalogram (EEG) is highly demanded. Traditional works classify EEG signals without considering the topological relationship among electrodes. However, neuroscience research has increasingly emphasized network patterns of brain dynamics. Thus, the Euclidean structure of electrodes might not adequately reflect the interaction between signals. To fill the gap, a novel deep learning (DL) framework based on the graph convolutional neural networks (GCNs) is presented to enhance the decoding performance of raw EEG signals during different types of motor imagery (MI) tasks while cooperating with the functional topological relationship of electrodes. Based on the absolute Pearson's matrix of overall signals, the graph Laplacian of EEG electrodes is built up. The GCNs-Net constructed by graph convolutional layers learns the generalized features. The followed pooling layers reduce dimensionality, and the fully-connected (FC) softmax layer derives the final prediction. The introduced approach has been shown to converge for both personalized and groupwise predictions. It has achieved the highest averaged accuracy, 93.06% and 88.57% (PhysioNet dataset), 96.24% and 80.89% (high gamma dataset), at the subject and group level, respectively, compared with existing studies, which suggests adaptability and robustness to individual variability. Moreover, the performance is stably reproducible among repetitive experiments for cross-validation. The excellent performance of our method has shown that it is an important step toward better BCI approaches. To conclude, the GCNs-Net filters EEG signals based on the functional topological relationship, which manages to decode relevant features for brain MI. A DL library for EEG task classification including the code for this study is open source at https://github.com/SuperBruceJia/ EEG-DL for scientific research.

In this paper, we propose a no-reference image quality assessment method based on non-local features learned by a graph neural network (GNN). The proposed quality assessment framework is rooted in the view that the human visual system perceives image quality with long-dependency constructed among different regions, inspiring us to explore the non-local interactions in quality prediction. Instead of relying on convolutional neural network (CNN) based quality assessment methods that primarily focus on local field features, the GNN aiming for non-local quality perception facilitates modeling such long-dependency. In particular, we first adopt superpixel segmentation for the graph nodes construction. Subsequently, a spatial attention module is proposed to integrate the long- and short-range dependencies among the nodes of the whole image. The learned non-local features are finally combined with the local features extracted by the pre-trained CNN, achieving superior performance to the features utilized individually. Experimental results on intra-dataset and cross-dataset settings verify our proposed method's effectiveness and advanced generalization capability. Source codes are publicly accessible at https://github.com/SuperBruceJia/NLNet-IQA for scientific reproducible research.