Search

We introduce DiffFNO, a novel diffusion framework for arbitrary-scale super-resolution strengthened by a Weighted Fourier Neural Operator (WFNO). Mode Re-balancing in WFNO effectively captures critical frequency components, significantly improving the reconstruction of high-frequency image details that are crucial for super-resolution tasks. Gated Fusion Mechanism (GFM) adaptively complements WFNO's spectral features with spatial features from an Attention-based Neural Operator (AttnNO). This enhances the network's capability to capture both global structures and local details. Adaptive Time-Step (ATS) ODE solver, a deterministic sampling strategy, accelerates inference without sacrificing output quality by dynamically adjusting integration step sizes ATS. Extensive experiments demonstrate that DiffFNO achieves state-of-the-art (SOTA) results, outperforming existing methods across various scaling factors by a margin of 2 to 4 dB in PSNR, including those beyond the training distribution. It also achieves this at lower inference time. Our approach sets a new standard in super-resolution, delivering both superior accuracy and computational efficiency.

Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous information, such as user profile and behavior sequences, depicts user interests from different aspects. A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction. However, most of the existing methods suffer from two fundamental limitations, including (1) insufficient inter-mode interaction due to the unidirectional information flow between modes, and (2) aggressive information aggregation caused by early summarization, resulting in excessive information loss. To address the above limitations, we propose a novel module named InterFormer to learn heterogeneous information interaction in an interleaving style. To achieve better interaction learning, InterFormer enables bidirectional information flow for mutually beneficial learning across different modes. To avoid aggressive information aggregation, we retain complete information in each data mode and use a separate bridging arch for effective information selection and summarization. Our proposed InterFormer achieves state-of-the-art performance on three public datasets and a large-scale industrial dataset., Comment: 10 pages, 6 figures

Ensuring safety on construction sites is critical, with helmets playing a key role in reducing injuries. Traditional safety checks are labor-intensive and often insufficient. This study presents a computer vision-based solution using YOLO for real-time helmet detection, leveraging the SHEL5K dataset. Our proposed CIB-SE-YOLOv8 model incorporates SE attention mechanisms and modified C2f blocks, enhancing detection accuracy and efficiency. This model offers a more effective solution for promoting safety compliance on construction sites., Comment: 5 pages, 5 figures

Gravitational R\'enyi computations have traditionally been described in the language of Euclidean path integrals. In the semiclassical limit, such calculations are governed by Euclidean (or, more generally, complex) saddle-point geometries. We emphasize here that, at least in simple contexts, the Euclidean approach suggests an alternative formulation in terms of the bulk quantum wavefunction. Since this alternate formulation can be directly applied to the real-time quantum theory, it is insensitive to subtleties involved in defining the Euclidean path integral. In particular, it can be consistent with many different choices of integration contour. Despite the fact that self-adjoint operators in the associated real-time quantum theory have real eigenvalues, we note that the bulk wavefunction encodes the Euclidean (or complex) R\'enyi geometries that would arise in any Euclidean path integral. As a result, for any given quantum state, the appropriate real-time path integral yields both R\'enyi entropies and associated complex saddle-point geometries that agree with Euclidean methods. After brief explanations of these general points, we use JT gravity to illustrate the associated real-time computations in detail., Comment: 36 pages + appendices, 24 figures

Incomplete knowledge of metabolic processes hinders the accuracy of GEnome-scale Metabolic models (GEMs), which in turn impedes advancements in systems biology and metabolic engineering. Existing gap-filling methods typically rely on phenotypic data to minimize the disparity between computational predictions and experimental results. However, there is still a lack of an automatic and precise gap-filling method for initial state GEMs before experimental data and annotated genomes become available. In this study, we introduce CLOSEgaps, a deep learning-driven tool that addresses the gap-filling issue by modeling it as a hyperedge prediction problem within GEMs. Specifically, CLOSEgaps maps metabolic networks as hypergraphs and learns their hyper-topology features to identify missing reactions and gaps by leveraging hypothetical reactions. This innovative approach allows for the characterization and curation of both known and hypothetical reactions within metabolic networks. Extensive results demonstrate that CLOSEgaps accurately gap-filling over 96% of artificially introduced gaps for various GEMs. Furthermore, CLOSEgaps enhances phenotypic predictions for 24 GEMs and also finds a notable improvement in producing four crucial metabolites (Lactate, Ethanol, Propionate, and Succinate) in two organisms. As a broadly applicable solution for any GEM, CLOSEgaps represents a promising model to automate the gap-filling process and uncover missing connections between reactions and observed metabolic phenotypes.

In e-commerce websites, web mining web page recommendation technology has been widely used. However, recommendation solutions often cannot meet the actual application needs of online shopping users. To address this problem, this paper proposes an e-commerce web page recommendation solution that combines semantic web mining and BP neural networks. First, the web logs of user searches are processed, and 5 features are extracted: content priority, time consumption priority, online shopping users' explicit/implicit feedback on the website, recommendation semantics and input deviation amount. Then, these features are used as input features of the BP neural network to classify and identify the priority of the final output web page. Finally, the web pages are sorted according to priority and recommended to users. This project uses book sales webpages as samples for experiments. The results show that this solution can quickly and accurately identify the webpages required by users., Comment: arXiv admin note: text overlap with arXiv:2409.01137

Skin lesions are an increasingly significant medical concern, varying widely in severity from benign to cancerous. Accurate diagnosis is essential for ensuring timely and appropriate treatment. This study examines the implementation of deep learning methods to assist in the diagnosis of skin lesions using the HAM10000 dataset, which contains seven distinct types of lesions. First, we evaluated three pre-trained models: MobileNetV2, ResNet18, and VGG11, achieving accuracies of 0.798, 0.802, and 0.805, respectively. To further enhance classification accuracy, we developed ensemble models employing max voting, average voting, and stacking, resulting in accuracies of 0.803, 0.82, and 0.83. Building on the best-performing ensemble learning model, stacking, we developed our proposed model, SkinNet, which incorporates a customized architecture and fine-tuning, achieving an accuracy of 0.867 and an AUC of 0.96. This substantial improvement over individual models demonstrates the effectiveness of ensemble learning in improving skin lesion classification.

Many people die from lung-related diseases every year. X-ray is an effective way to test if one is diagnosed with a lung-related disease or not. This study concentrates on categorizing three distinct types of lung X-rays: those depicting healthy lungs, those showing lung opacities, and those indicative of viral pneumonia. Accurately diagnosing the disease at an early phase is critical. In this paper, five different pre-trained models will be tested on the Lung X-ray Image Dataset. SqueezeNet, VGG11, ResNet18, DenseNet, and MobileNetV2 achieved accuracies of 0.64, 0.85, 0.87, 0.88, and 0.885, respectively. MobileNetV2, as the best-performing pre-trained model, will then be further analyzed as the base model. Eventually, our own model, MobileNet-Lung based on MobileNetV2, with fine-tuning and an additional layer of attention within feature layers, was invented to tackle the lung disease classification task and achieved an accuracy of 0.933. This result is significantly improved compared with all five pre-trained models.

A long-standing challenge in end-user programming (EUP) is to trade off between natural user expression and the complexity of programming tasks. As large language models (LLMs) are empowered to handle semantic inference and natural language understanding, it remains under-explored how such capabilities can facilitate end-users to configure complex automation more naturally and easily. We propose AwareAuto, an EUP system that standardizes user expression and finishes two-step inference with the LLMs to achieve automation generation. AwareAuto allows contextual, multi-modality, and flexible user expression to configure complex automation tasks (e.g., dynamic parameters, multiple conditional branches, and temporal constraints), which are non-manageable in traditional EUP solutions. By studying realistic, complex rules data, AwareAuto gains 91.7% accuracy in matching user intentions and feasibility. We introduced user interaction to ensure system controllability and usability. We discuss the opportunities and challenges of incorporating LLMs in end-user programming techniques and grounding complex smart home contexts.

Temporal knowledge graph completion aims to infer the missing facts in temporal knowledge graphs. Current approaches usually embed factual knowledge into continuous vector space and apply geometric operations to learn potential patterns in temporal knowledge graphs. However, these methods only adopt a single operation, which may have limitations in capturing the complex temporal dynamics present in temporal knowledge graphs. Therefore, we propose a simple but effective method, i.e. TCompoundE, which is specially designed with two geometric operations, including time-specific and relation-specific operations. We provide mathematical proofs to demonstrate the ability of TCompoundE to encode various relation patterns. Experimental results show that our proposed model significantly outperforms existing temporal knowledge graph embedding models. Our code is available at https://github.com/nk-ruiying/TCompoundE.

Brain tumors are among the deadliest diseases in the world. Magnetic Resonance Imaging (MRI) is one of the most effective ways to detect brain tumors. Accurate detection of brain tumors based on MRI scans is critical, as it can potentially save many lives and facilitate better decision-making at the early stages of the disease. Within our paper, four different types of MRI-based images have been collected from the database: glioma tumor, no tumor, pituitary tumor, and meningioma tumor. Our study focuses on making predictions for brain tumor classification. Five models, including four pre-trained models (MobileNet, EfficientNet-B0, ResNet-18, and VGG16) and one new model, MobileNet-BT, have been proposed for this study.

With the rapid advancement of deep learning technologies, computer vision has shown immense potential in retail automation. This paper presents a novel self-checkout system for retail based on an improved YOLOv10 network, aimed at enhancing checkout efficiency and reducing labor costs. We propose targeted optimizations to the YOLOv10 model, by incorporating the detection head structure from YOLOv8, which significantly improves product recognition accuracy. Additionally, we develop a post-processing algorithm tailored for self-checkout scenarios, to further enhance the application of system. Experimental results demonstrate that our system outperforms existing methods in both product recognition accuracy and checkout speed. This research not only provides a new technical solution for retail automation but offers valuable insights into optimizing deep learning models for real-world applications.

The 3D simulation model of the lung was established by using the reconstruction method. A computer aided pulmonary nodule detection model was constructed. The process iterates over the images to refine the lung nodule recognition model based on neural networks. It is integrated with 3D virtual modeling technology to improve the interactivity of the system, so as to achieve intelligent recognition of lung nodules. A 3D RCNN (Region-based Convolutional Neural Network) was utilized for feature extraction and nodule identification. The LUNA16 large sample database was used as the research dataset. FROC (Free-response Receiver Operating Characteristic) analysis was applied to evaluate the model, calculating sensitivity at various false positive rates to derive the average FROC. Compared with conventional diagnostic methods, the recognition rate was significantly improved. This technique facilitates the detection of pulmonary abnormalities at an initial phase, which holds immense value for the prompt diagnosis of lung malignancies.

Aspect sentiment quad prediction (ASQP) aims to predict four aspect-based elements, including aspect term, opinion term, aspect category, and sentiment polarity. In practice, unseen aspects, due to distinct data distribution, impose many challenges for a trained neural model. Motivated by this, this work formulates ASQP into the few-shot scenario, which aims for fast adaptation in real applications. Therefore, we first construct a few-shot ASQP dataset (FSQP) that contains richer categories and is more balanced for the few-shot study. Moreover, recent methods extract quads through a generation paradigm, which involves converting the input sentence into a templated target sequence. However, they primarily focus on the utilization of a single template or the consideration of different template orders, thereby overlooking the correlations among various templates. To tackle this issue, we further propose a Broadview Soft Prompting (BvSP) method that aggregates multiple templates with a broader view by taking into account the correlation between the different templates. Specifically, BvSP uses the pre-trained language model to select the most relevant k templates with Jensen-Shannon divergence. BvSP further introduces soft prompts to guide the pre-trained language model using the selected templates. Then, we aggregate the results of multi-templates by voting mechanism. Empirical results demonstrate that BvSP significantly outperforms the stateof-the-art methods under four few-shot settings and other public datasets. Our code and dataset are available at https://github.com/byinhao/BvSP., Comment: Accepted to ACL 2024 Main Conference

This paper introduces an innovative multi-modal fusion deep learning approach to overcome the drawbacks of traditional single-modal recognition techniques. These drawbacks include incomplete information and limited diagnostic accuracy. During the feature extraction stage, cutting-edge deep learning models including convolutional neural networks (CNN), recurrent neural networks (RNN), and transformers are applied to distill advanced features from image-based, temporal, and structured data sources. The fusion strategy component seeks to determine the optimal fusion mode tailored to the specific disease recognition task. In the experimental section, a comparison is made between the performance of the proposed multi-mode fusion model and existing single-mode recognition methods. The findings demonstrate significant advantages of the multimodal fusion model across multiple evaluation metrics.

Spacetime wormholes can provide non-perturbative contributions to the gravitational path integral that make the actual number of states $e^S$ in a gravitational system much smaller than the number of states $e^{S_{\mathrm{p}}}$ predicted by perturbative semiclassical effective field theory. The effects on the physics of the system are naturally profound in contexts in which the perturbative description actively involves $N = O(e^S)$ of the possible $e^{S_{\mathrm{p}}}$ perturbative states; e.g., in late stages of black hole evaporation. Such contexts are typically associated with the existence of non-trivial quantum extremal surfaces. However, by forcing a simple topological gravity model to evolve in time, we find that such effects can also have large impact for $N\ll e^S$ (in which case no quantum extremal surfaces can arise). In particular, even for small $N$, the insertion of generic operators into the path integral can cause the non-perturbative time evolution to differ dramatically from perturbative expectations. On the other hand, this discrepancy is small for the special case where the inserted operators are non-trivial only in a subspace of dimension $D \ll e^S$. We thus study this latter case in detail. We also discuss potential implications for more realistic gravitational systems., Comment: 30 pages, 11 figures

We consider four-dimensional Euclidean gravity in a finite cavity. Dirichlet conditions do not yield a well-posed elliptic system, and Anderson has suggested boundary conditions that do. Here we point out that there exists a one-parameter family of boundary conditions, parameterized by a constant $p$, where a suitably Weyl rescaled boundary metric is fixed, and all give a well-posed elliptic system. Anderson and Dirichlet boundary conditions can be seen as the limits $p \to 0$ and $\infty$ of these. Focussing on static Euclidean solutions, we derive a thermodynamic first law. Restricting to a spherical spatial boundary, the infillings are flat space or the Schwarzschild solution, and have similar thermodynamics to the Dirichlet case. We consider smooth Euclidean fluctuations about the flat space saddle; for $p > 1/6$ the spectrum of the Lichnerowicz operator is stable -- its eigenvalues have positive real part. Thus we may regard large $p$ as a regularization of the ill-posed Dirichlet boundary conditions. However for $p < 1/6$ there are unstable modes, even in the spherically symmetric and static sector. We then turn to Lorentzian signature. For $p < 1/6$ we may understand this spherical Euclidean instability as being paired with a Lorentzian instability associated with the dynamics of the boundary itself. However, a mystery emerges when we consider perturbations that break spherical symmetry. Here we find a plethora of dynamically unstable modes even for $p > 1/6$, contrasting starkly with the Euclidean stability we found. Thus we seemingly obtain a system with stable thermodynamics, but unstable dynamics, calling into question the standard assumption of smoothness that we have implemented when discussing the Euclidean theory., Comment: 45+30 pages, 20 figures; v2 references added

As a new communication paradigm, semantic communication has received widespread attention in communication fields. However, since the decoding of semantic signals relies on contextual knowledge, misalignment between the starting position of the semantic signal and the AI-based semantic decoder would prevent source signal recovery and reconstruction. To achieve more precise semantic communication, this study proposes an image-based semantic synchronization method leveraging intrinsic semantic features of image content. Specifically, a shared synchronized image (SyncImg) is encoded into a synchronization vector header at the transmitter and sent to the receiver. The receiver adopts a sliding window semantic decoder combined with classification and template matching methods to locate the synchronization point. Experimental results demonstrate that compared with traditional methods, the proposed method achieves a lower miss detected ratio (MDR) and root-mean-square error (RMSE) under low signal-to-noise ratios, realizing accurate synchronization of semantic signals across different devices.

Due to the conformal factor problem, the definition of the Euclidean gravitational path integral requires a non-trivial choice of contour. The present work examines a generalization of a recently proposed rule-of-thumb \cite{Marolf:2022ntb} for selecting this contour at quadratic order about a saddle. The original proposal depended on the choice of an indefinite-signature metric on the space of perturbations, which was taken to be a DeWitt metric with parameter $\alpha =-1$. This choice was made to match previous results, but was otherwise admittedly {\it ad hoc}. To begin to investigate the physics associated with the choice of such a metric, we now explore contours defined using analogous prescriptions for $\alpha \neq -1$. We study such contours for Euclidean gravity linearized about AdS-Schwarzschild black holes in reflecting cavities with thermal (canonical ensemble) boundary conditions, and we compare path-integral stability of the associated saddles with thermodynamic stability of the classical spacetimes. While the contour generally depends on the choice of DeWitt parameter $\alpha$, the precise agreement between these two notions of stability found at $\alpha =-1$ continues to hold over the finite interval $(-2,-2/d)$, where $d$ is the dimension of the bulk spacetime. This agreement manifestly fails for $\alpha > -2/d$ when the DeWitt metric becomes positive definite. However, we also find dramatic failures for $\alpha< -2$ that correlate with breakdowns of the de Donder-like gauge condition defined by $\alpha$, and at which the relevant fluctuation operator fails to be diagonalizable. This provides criteria that may be useful in predicting metrics on the space of perturbations that give physically-useful contours in more general settings. Along the way, we also identify an interesting error in \cite{Marolf:2022ntb}, though we show this error to be harmless., Comment: 32 pages, 13 figures

Point cloud, as a 3D representation, is widely used in autonomous driving, virtual reality (VR), and augmented reality (AR). However, traditional communication systems think that the point cloud's semantic information is irrelevant to communication, which hinders the efficient transmission of point clouds in the era of artificial intelligence (AI). This paper proposes a point cloud based semantic communication system (PCSC), which uses AI-based encoding techniques to extract the semantic information of the point cloud and joint source-channel coding (JSCC) technology to overcome the distortion caused by noise channels and solve the "cliff effect" in traditional communication. In addition, the system realizes the controllable coding rate without fine-tuning the network. The method analyzes the coded semantic vector's importance and discards semantically-unimportant information, thereby improving the transmission efficiency. Besides, PCSC and the recently proposed non-orthogonal model division multiple access (MDMA) technology are combined to design a point cloud MDMA transmission system (M-PCSC) for multi-user transmission. Relevant experimental results show that the proposed method outperforms the traditional method 10dB in the same channel bandwidth ratio under the PSNR D1 and PSNR D2 metrics. In terms of transmission, the proposed method can effectively solve the "cliff effect" in the traditional methods.

Time-series prediction has drawn considerable attention during the past decades fueled by the emerging advances of deep learning methods. However, most neural network based methods lack interpretability and fail in extracting the hidden mechanism of the targeted physical system. To overcome these shortcomings, an interpretable sparse system identification method without any prior knowledge is proposed in this study. This method adopts the Fourier transform to reduces the irrelevant items in the dictionary matrix, instead of indiscriminate usage of polynomial functions in most system identification methods. It shows an interpretable system representation and greatly reduces computing cost. With the adoption of $l_1$ norm in regularizing the parameter matrix, a sparse description of the system model can be achieved. Moreover, Three data sets including the water conservancy data, global temperature data and financial data are used to test the performance of the proposed method. Although no prior knowledge was known about the physical background, experimental results show that our method can achieve long-term prediction regardless of the noise and incompleteness in the original data more accurately than the widely-used baseline data-driven methods. This study may provide some insight into time-series prediction investigations, and suggests that an white-box system identification method may extract the easily overlooked yet inherent periodical features and may beat neural-network based black-box methods on long-term prediction tasks.

Free-space optical communication (FSO) can achieve fast, secure and license-free communication without need for physical cables, making it a cost-effective, energy-efficient and flexible solution when the fiber connection is unavailable. To establish FSO connection on-demand, it is essential to build portable FSO devices with compact structure and light weight. Here, we develop a miniaturized FSO system and realize 9.16 Gbps FSO between two nodes that is 1 km apart, using a commercial single-mode-fiber-coupled optical transceiver module without optical amplification. Using our 4-stage acquisition, pointing and tracking (APT) systems, the tracking error is within 3 {\mu}rad and results an average link loss of 13.7 dB, which is the key for this high-bandwidth FSO demonstration without optical amplification. Our FSO link has been tested up to 4 km, with link loss of 18 dB that is limited by the foggy weather during the test. Longer FSO distances can be expected with better weather condition and optical amplification. With single FSO device weight of only 9.5 kg, this result arouses massive applications of field-deployable high-speed wireless communication., Comment: 7 pages, 5 figures

Large-photon-number quantum state is a fundamental but non-resolved request for practical quantum information applications. Here we propose an N-photon state generation scheme that is feasible and scalable, using lithium niobate on insulator circuits. Such scheme is based on the integration of a common building block called photon-number doubling unit (PDU), for deterministic single-photon parametric down-conversion and up-conversion. The PDU relies on 10^7-optical-quality-factor resonator and mW-level on-chip power, which is within the current fabrication and experiment limits. N-photon state generation schemes, with cluster and GHZ state as examples, are shown for different quantum tasks.

In this paper, we present NxtPost, a deployed user-to-post content-based sequential recommender system for Facebook Groups. Inspired by recent advances in NLP, we have adapted a Transformer-based model to the domain of sequential recommendation. We explore causal masked multi-head attention that optimizes both short and long-term user interests. From a user's past activities validated by defined safety process, NxtPost seeks to learn a representation for the user's dynamic content preference and to predict the next post user may be interested in. In contrast to previous Transformer-based methods, we do not assume that the recommendable posts have a fixed corpus. Accordingly, we use an external item/token embedding to extend a sequence-based approach to a large vocabulary. We achieve 49% abs. improvement in offline evaluation. As a result of NxtPost deployment, 0.6% more users are meeting new people, engaging with the community, sharing knowledge and getting support. The paper shares our experience in developing a personalized sequential recommender system, lessons deploying the model for cold start users, how to deal with freshness, and tuning strategies to reach higher efficiency in online A/B experiments., Comment: 9 pages