Motivation: Electronic Health Records (EHR) represent a comprehensive resource of a patient's medical history. EHR are essential for utilizing advanced technologies such as deep learning (DL), enabling healthcare providers to analyze extensive data, extract valuable insights, and make precise and data-driven clinical decisions. DL methods such as Recurrent Neural Networks (RNN) have been utilized to analyze EHR to model disease progression and predict diagnosis. However, these methods do not address some inherent irregularities in EHR data such as irregular time intervals between clinical visits. Furthermore, most DL models are not interpretable. In this study, we propose two interpretable DL architectures based on RNN, namely Time-Aware RNN (TA-RNN) and TA-RNN-Autoencoder (TA-RNN-AE) to predict patient's clinical outcome in EHR at next visit and multiple visits ahead, respectively. To mitigate the impact of irregular time intervals, we propose incorporating time embedding of the elapsed times between visits. For interpretability, we propose employing a dual-level attention mechanism that operates between visits and features within each visit. Results: The results of the experiments conducted on Alzheimer's Disease Neuroimaging Initiative (ADNI) and National Alzheimer's Coordinating Center (NACC) datasets indicated superior performance of proposed models for predicting Alzheimer's Disease (AD) compared to state-of-the-art and baseline approaches based on F2 and sensitivity. Additionally, TA-RNN showed superior performance on Medical Information Mart for Intensive Care (MIMIC-III) dataset for mortality prediction. In our ablation study, we observed enhanced predictive performance by incorporating time embedding and attention mechanisms. Finally, investigating attention weights helped identify influential visits and features in predictions.
Extended reality (XR) is one of the most important applications of 5G. For real-time XR video transmission in 5G networks, a low latency and high data rate are required. In this paper, we propose a resource allocation scheme based on frame-priority scheduling to meet these requirements. The optimization problem is modelled as a frame-priority-based radio resource scheduling problem to improve transmission quality. We propose a scheduling framework based on multi-step Deep Q-network (MS-DQN) and design a neural network model based on convolutional neural network (CNN). Simulation results show that the scheduling framework based on frame-priority and MS-DQN can improve transmission quality by 49.9%-80.2%.
The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations. Existing methods, however, fail to address these challenges appropriately. On the one hand, they usually recast RTE task to text-to-text prompting formats, which is unnatural and results in a mismatch between the output format at the pre-training time and the inference time for large language models (LLMs). On the other hand, they only utilize surface natural language features and lack consideration of triple semantics in sample selection. These issues are blocking improved performance in ICL for RTE, thus we aim to tackle prompt designing and sample selection challenges simultaneously. To this end, we devise a tabular prompting for RTE (\textsc{TableIE}) which frames RTE task into a table generation task to incorporate explicit structured information into ICL, facilitating conversion of outputs to RTE structures. Then we propose instructive in-context learning (I$^2$CL) which only selects and annotates a few samples considering internal triple semantics in massive unlabeled samples.
Drafting-then-verifying decoding methods such as speculative decoding are widely adopted training-free methods to accelerate the inference of large language models (LLMs). Instead of employing an autoregressive process to decode tokens sequentially, speculative decoding initially creates drafts with an efficient small model. Then LLMs are required to conduct verification and correction in a non-autoregressive fashion to minimize time overhead. Generating longer drafts can lead to even more significant speedups once verified, but also incurs substantial trial and error costs if it fails. Suffering from the high verification failure probability, existing decoding methods cannot draft too much content for verification at one time, achieving sub-optimal inference acceleration. In this paper, we introduce Ouroboros, which constructs a phrase candidate pool from the verification process of LLMs to provide candidates for draft generation of the small model. Thereby, Ouroboros can further improve the efficiency and effectiveness of the initial drafts. The experimental results on typical text generation tasks show that Ouroboros achieves speedups of up to 1.9x and 2.8x compared to lookahead decoding and speculative decoding, respectively. The source code of Ouroboros is available at https://github.com/thunlp/Ouroboros.
In recent years, both online and offline deep learning models have been developed for time series forecasting. However, offline deep forecasting models fail to adapt effectively to changes in time-series data, while online deep forecasting models are often expensive and have complex training procedures. In this paper, we reframe the online nonlinear time-series forecasting problem as one of linear hyperdimensional time-series forecasting. Nonlinear low-dimensional time-series data is mapped to high-dimensional (hyperdimensional) spaces for linear hyperdimensional prediction, allowing fast, efficient and lightweight online time-series forecasting. Our framework, TSF-HD, adapts to time-series distribution shifts using a novel co-training framework for its hyperdimensional mapping and its linear hyperdimensional predictor. TSF-HD is shown to outperform the state of the art, while having reduced inference latency, for both short-term and long-term time series forecasting. Our code is publicly available at http://github.com/tsfhd2024/tsf-hd.git
We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision. UFO employs a dual-agent framework to meticulously observe and analyze the graphical user interface (GUI) and control information of Windows applications. This enables the agent to seamlessly navigate and operate within individual applications and across them to fulfill user requests, even when spanning multiple applications. The framework incorporates a control interaction module, facilitating action grounding without human intervention and enabling fully automated execution. Consequently, UFO transforms arduous and time-consuming processes into simple tasks achievable solely through natural language commands. We conducted testing of UFO across 9 popular Windows applications, encompassing a variety of scenarios reflective of users' daily usage. The results, derived from both quantitative metrics and real-case studies, underscore the superior effectiveness of UFO in fulfilling user requests. To the best of our knowledge, UFO stands as the first UI agent specifically tailored for task completion within the Windows OS environment. The open-source code for UFO is available on https://github.com/microsoft/UFO.
The identification and characterization of various rock types is one of the fundamental activities for geology and related areas such as mining, petroleum, environment, industry and construction. Traditionally, a human specialist is responsible for analyzing and explaining details about the type, composition, texture, shape and other properties using rock samples collected in-situ or prepared in a laboratory. The results become subjective based on experience, in addition to consuming a large investment of time and effort. The present proposal uses artificial intelligence techniques combining computer vision and natural language processing to generate a textual and verbal description from a thin section image of rock. We build a dataset of images and their respective textual descriptions for the training of a model that associates the relevant features of the image extracted by EfficientNetB7 with the textual description generated by a Transformer network, reaching an accuracy value of 0.892 and a BLEU value of 0.71. This model can be a useful resource for research, professional and academic work, so it has been deployed through a Web application for public use.
Developing an accurate and fast anomaly detection model is an important task in real-time computer vision applications. There has been much research to develop a single model that detects either structural or logical anomalies, which are inherently distinct. The majority of the existing approaches implicitly assume that the anomaly can be represented by identifying the anomalous location. However, we argue that logical anomalies, such as the wrong number of objects, can not be well-represented by the spatial feature maps and require an alternative approach. In addition, we focused on the possibility of detecting logical anomalies by using an out-of-distribution detection approach on the feature space, which aggregates the spatial information of the feature map. As a demonstration, we propose a method that incorporates a simple out-of-distribution detection method on the feature space against state-of-the-art reconstruction-based approaches. Despite the simplicity of our proposal, our method PUAD (Picturable and Unpicturable Anomaly Detection) achieves state-of-the-art performance on the MVTec LOCO AD dataset.
In autonomous driving, cooperative perception makes use of multi-view cameras from both vehicles and infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint. Currently, two major challenges persist in vehicle-infrastructure cooperative 3D (VIC3D) object detection: $1)$ inherent pose errors when fusing multi-view images, caused by time asynchrony across cameras; $2)$ information loss in transmission process resulted from limited communication bandwidth. To address these issues, we propose a novel camera-based 3D detection framework for VIC3D task, Enhanced Multi-scale Image Feature Fusion (EMIFF). To fully exploit holistic perspectives from both vehicles and infrastructure, we propose Multi-scale Cross Attention (MCA) and Camera-aware Channel Masking (CCM) modules to enhance infrastructure and vehicle features at scale, spatial, and channel levels to correct the pose error introduced by camera asynchrony. We also introduce a Feature Compression (FC) module with channel and spatial compression blocks for transmission efficiency. Experiments show that EMIFF achieves SOTA on DAIR-V2X-C datasets, significantly outperforming previous early-fusion and late-fusion methods with comparable transmission costs.
Automatic evaluation methods for large language models (LLMs) are hindered by data contamination, leading to inflated assessments of their effectiveness. Existing strategies, which aim to detect contaminated texts, focus on quantifying contamination status instead of accurately gauging model performance. In this paper, we introduce KIEval, a Knowledge-grounded Interactive Evaluation framework, which incorporates an LLM-powered "interactor" role for the first time to accomplish a dynamic contamination-resilient evaluation. Starting with a question in a conventional LLM benchmark involving domain-specific knowledge, KIEval utilizes dynamically generated, multi-round, and knowledge-focused dialogues to determine whether a model's response is merely a recall of benchmark answers or demonstrates a deep comprehension to apply knowledge in more complex conversations. Extensive experiments on seven leading LLMs across five datasets validate KIEval's effectiveness and generalization. We also reveal that data contamination brings no contribution or even negative effect to models' real-world applicability and understanding, and existing contamination detection methods for LLMs can only identify contamination in pre-training but not during supervised fine-tuning.