Search

Human cognition can leverage fundamental conceptual knowledge, like geometric and kinematic ones, to appropriately perceive, comprehend and interact with novel objects. Motivated by this finding, we aim to endow machine intelligence with an analogous capability through performing at the conceptual level, in order to understand and then interact with articulated objects, especially for those in novel categories, which is challenging due to the intricate geometric structures and diverse joint types of articulated objects. To achieve this goal, we propose Analytic Ontology Template (AOT), a parameterized and differentiable program description of generalized conceptual ontologies. A baseline approach called AOTNet driven by AOTs is designed accordingly to equip intelligent agents with these generalized concepts, and then empower the agents to effectively discover the conceptual knowledge on the structure and affordance of articulated objects. The AOT-driven approach yields benefits in three key perspectives: i) enabling concept-level understanding of articulated objects without relying on any real training data, ii) providing analytic structure information, and iii) introducing rich affordance information indicating proper ways of interaction. We conduct exhaustive experiments and the results demonstrate the superiority of our approach in understanding and then interacting with articulated objects.

Few-shot class-incremental learning is crucial for developing scalable and adaptive intelligent systems, as it enables models to acquire new classes with minimal annotated data while safeguarding the previously accumulated knowledge. Nonetheless, existing methods deal with continuous data streams in a centralized manner, limiting their applicability in scenarios that prioritize data privacy and security. To this end, this paper introduces federated few-shot class-incremental learning, a decentralized machine learning paradigm tailored to progressively learn new classes from scarce data distributed across multiple clients. In this learning paradigm, clients locally update their models with new classes while preserving data privacy, and then transmit the model updates to a central server where they are aggregated globally. However, this paradigm faces several issues, such as difficulties in few-shot learning, catastrophic forgetting, and data heterogeneity. To address these challenges, we present a synthetic data-driven framework that leverages replay buffer data to maintain existing knowledge and facilitate the acquisition of new knowledge. Within this framework, a noise-aware generative replay module is developed to fine-tune local models with a balance of new and replay data, while generating synthetic data of new classes to further expand the replay buffer for future tasks. Furthermore, a class-specific weighted aggregation strategy is designed to tackle data heterogeneity by adaptively aggregating class-specific parameters based on local models performance on synthetic data. This enables effective global model optimization without direct access to client data. Comprehensive experiments across three widely-used datasets underscore the effectiveness and preeminence of the introduced framework.

Semi-Supervised Learning (SSL) has become a preferred paradigm in many deep learning tasks, which reduces the need for human labor. Previous studies primarily focus on effectively utilising the labelled and unlabeled data to improve performance. However, we observe that how to select samples for labelling also significantly impacts performance, particularly under extremely low-budget settings. The sample selection task in SSL has been under-explored for a long time. To fill in this gap, we propose a Representative and Diverse Sample Selection approach (RDSS). By adopting a modified Frank-Wolfe algorithm to minimise a novel criterion $\alpha$-Maximum Mean Discrepancy ($\alpha$-MMD), RDSS samples a representative and diverse subset for annotation from the unlabeled data. We demonstrate that minimizing $\alpha$-MMD enhances the generalization ability of low-budget learning. Experimental results show that RDSS consistently improves the performance of several popular SSL frameworks and outperforms the state-of-the-art sample selection approaches used in Active Learning (AL) and Semi-Supervised Active Learning (SSAL), even with constrained annotation budgets., Comment: Under Review

This paper provides a comprehensive overview of the principles, challenges, and methodologies associated with quantizing large-scale neural network models. As neural networks have evolved towards larger and more complex architectures to address increasingly sophisticated tasks, the computational and energy costs have escalated significantly. We explore the necessity and impact of model size growth, highlighting the performance benefits as well as the computational challenges and environmental considerations. The core focus is on model quantization as a fundamental approach to mitigate these challenges by reducing model size and improving efficiency without substantially compromising accuracy. We delve into various quantization techniques, including both post-training quantization (PTQ) and quantization-aware training (QAT), and analyze several state-of-the-art algorithms such as LLM-QAT, PEQA(L4Q), ZeroQuant, SmoothQuant, and others. Through comparative analysis, we examine how these methods address issues like outliers, importance weighting, and activation quantization, ultimately contributing to more sustainable and accessible deployment of large-scale models.

Rb-82 is a radioactive isotope widely used for cardiac PET imaging. Despite numerous benefits of 82-Rb, there are several factors that limits its image quality and quantitative accuracy. First, the short half-life of 82-Rb results in noisy dynamic frames. Low signal-to-noise ratio would result in inaccurate and biased image quantification. Noisy dynamic frames also lead to highly noisy parametric images. The noise levels also vary substantially in different dynamic frames due to radiotracer decay and short half-life. Existing denoising methods are not applicable for this task due to the lack of paired training inputs/labels and inability to generalize across varying noise levels. Second, 82-Rb emits high-energy positrons. Compared with other tracers such as 18-F, 82-Rb travels a longer distance before annihilation, which negatively affect image spatial resolution. Here, the goal of this study is to propose a self-supervised method for simultaneous (1) noise-aware dynamic image denoising and (2) positron range correction for 82-Rb cardiac PET imaging. Tested on a series of PET scans from a cohort of normal volunteers, the proposed method produced images with superior visual quality. To demonstrate the improvement in image quantification, we compared image-derived input functions (IDIFs) with arterial input functions (AIFs) from continuous arterial blood samples. The IDIF derived from the proposed method led to lower AUC differences, decreasing from 11.09% to 7.58% on average, compared to the original dynamic frames. The proposed method also improved the quantification of myocardium blood flow (MBF), as validated against 15-O-water scans, with mean MBF differences decreased from 0.43 to 0.09, compared to the original dynamic frames. We also conducted a generalizability experiment on 37 patient scans obtained from a different country using a different scanner., Comment: 15 Pages, 10 Figures, 5 tables. Paper Under review. Oral Presentation at IEEE MIC 2023

Hallucination, the generation of factually incorrect content, is a growing challenge in Large Language Models (LLMs). Existing detection and mitigation methods are often isolated and insufficient for domain-specific needs, lacking a standardized pipeline. This paper introduces THaMES (Tool for Hallucination Mitigations and EvaluationS), an integrated framework and library addressing this gap. THaMES offers an end-to-end solution for evaluating and mitigating hallucinations in LLMs, featuring automated test set generation, multifaceted benchmarking, and adaptable mitigation strategies. It automates test set creation from any corpus, ensuring high data quality, diversity, and cost-efficiency through techniques like batch processing, weighted sampling, and counterfactual validation. THaMES assesses a model's ability to detect and reduce hallucinations across various tasks, including text generation and binary classification, applying optimal mitigation strategies like In-Context Learning (ICL), Retrieval Augmented Generation (RAG), and Parameter-Efficient Fine-tuning (PEFT). Evaluations of state-of-the-art LLMs using a knowledge base of academic papers, political news, and Wikipedia reveal that commercial models like GPT-4o benefit more from RAG than ICL, while open-weight models like Llama-3.1-8B-Instruct and Mistral-Nemo gain more from ICL. Additionally, PEFT significantly enhances the performance of Llama-3.1-8B-Instruct in both evaluation tasks., Comment: Submitted to NeurIPS 2024 SoLaR (Socially Responsible Language Modelling Research ) Workshop

In the milli-Hertz frequency band, stochastic gravitational-wave background can be composed of both astronomical and cosmological sources, both can be anisotropic. Numerically depicting these anisotropies can be critical in revealing the underlying properties of their origins. For the first time, we perform a theoretical analysis of the constraining ability of TianQin on multiple moments of the stochastic background. First, we find that with a one-year operation, for a background with a signal-to-noise ratio of 16, TianQin can recover the multiple moments up to $l=4$. We also identified a unique feature of the stochastic background sky map, which is the mirror symmetry along the fixed orbital plane of TianQin. Thirdly, we explain the difference in anisotropy recovering ability between TianQin and LISA, by employing the criteria of the singularity of the covariance matrix (which is the condition number). Finally, we find that since the different data channel combinations correspond to different singularities, certain combinations might have an advantage in stochastic background map-making. We believe that the findings of this work can provide an important reference to future stochastic background analysis pipelines. It can also serve as a guideline for designing better gravitational-wave detectors aiming to decipher anisotropies in the stochastic background., Comment: 12 pages, 6 figures

With the emergence of integrated sensing, communication, and computation (ISCC) in the upcoming 6G era, federated learning with ISCC (FL-ISCC), integrating sample collection, local training, and parameter exchange and aggregation, has garnered increasing interest for enhancing training efficiency. Currently, FL-ISCC primarily includes two algorithms: FedAVG-ISCC and FedSGD-ISCC. However, the theoretical understanding of the performance and advantages of these algorithms remains limited. To address this gap, we investigate a general FL-ISCC framework, implementing both FedAVG-ISCC and FedSGD-ISCC. We experimentally demonstrate the substantial potential of the ISCC framework in reducing latency and energy consumption in FL. Furthermore, we provide a theoretical analysis and comparison. The results reveal that:1) Both sample collection and communication errors negatively impact algorithm performance, highlighting the need for careful design to optimize FL-ISCC applications. 2) FedAVG-ISCC performs better than FedSGD-ISCC under IID data due to its advantage with multiple local updates. 3) FedSGD-ISCC is more robust than FedAVG-ISCC under non-IID data, where the multiple local updates in FedAVG-ISCC worsen performance as non-IID data increases. FedSGD-ISCC maintains performance levels similar to IID conditions. 4) FedSGD-ISCC is more resilient to communication errors than FedAVG-ISCC, which suffers from significant performance degradation as communication errors increase.Extensive simulations confirm the effectiveness of the FL-ISCC framework and validate our theoretical analysis., Comment: due to the limitation The abstract field cannot be longer than 1,920 characters", the abstract appearing here is slightly shorter than that in the PDF file

The standard $\rm \Lambda$CDM cosmological model predicts that a large amount of diffuse neutral hydrogen distributes in cosmic filaments, which could be mapped through Lyman-alpha (Ly$\alpha$) emission observations. We use the hydrodynamical simulation Illustris-TNG50 to investigate the evolution of surface brightness and detectability of neutral hydrogen in cosmic filaments across redshifts $z=2-5$. While the HI column density of cosmic filaments decreases with redshift, due to the rising temperature with cosmic time in filaments, the surface brightness of Ly$\alpha$ emission in filaments is brighter at lower redshifts, suggesting that the detection of cosmic filaments is more feasible at lower redshifts. However, most of the Ly$\alpha$ emission from cosmic filaments is around $10^{-21}$ $\rm erg\ s^{-1}cm^{-2}arsec^{-2}$, making it extremely challenging to detect with current observational instruments. We further generate mock images using the Multi-Unit Spectroscopic Explorer (MUSE) spectrograph installed on both the Very Large Telescope (VLT) and the upcoming Extremely Large Telescope (ELT). Our finding indicates that while the VLT can only detect filamentary structures made of dense gas in galactic centers, the ELT is expected to reveal much finer filamentary structures from diffuse neutral hydrogen outside of galaxies. Compared to the VLT, both the number density and the longest length of filaments are greatly boosted with the ELT. Hence the forthcoming ELT is highly promising to provide a clearer view of cosmic filaments in Ly$\alpha$ emission.

The cosmic gravitational focusing (CGF) of relic neutrinos can provide an independent measurement of the absolute neutrino masses $m_i$ with fourth-power dependence ($m^4_i$). We demonstrate in this paper for the first time how this can help identifying the neutrino mass ordering (NMO). Upon incorporating the projected CGF sensitivity at DESI, the preference for the normal ordering (NO) with a prior $\sum m_\nu > 0.509\,{\rm eV}$ would increase from the original 89.9\% of the current clustering method with both DESI BAO and CMB to 98.2\% while the inverted ordering (IO) is further disfavored from 10.1\% to 1.8\%. We also show how this can affect the prospects of the neutrinoless double beta decay and single beta decay measurements., Comment: 14 pages, 7 figures

The recent discovery of gravitational waves (GWs) has opened a new avenue for investigating the equation of state (EOS) of dense matter in compact stars, which is an outstanding problem in astronomy and nuclear physics. In the future, next-generation (XG) GW detectors will be constructed, deemed to provide a large number of high-precision observations. We investigate the potential of constraining the EOS of quark stars (QSs) with high-precision measurements of mass $m$ and tidal deformability $\Lambda$ from the XG GW observatories. We adopt the widely-used bag model for QSs, consisting of four microscopic parameters: the effective bag constant $B_{\rm eff}$, the perturbative quantum chromodynamics correction parameter $a_4$, the strange quark mass $m_s$, and the pairing energy gap $\Delta$. With the help of hierarchical Bayesian inference, for the first time we are able to infer the EOS of QSs combining multiple GW observations. Using the top 25 loudest GW events in our simulation, we find that, the constraints on $B_{\rm eff}$ and $\Delta$ are tightened by several times, while $a_4$ and $m_s$ are still poorly constrained. We also study a simplified 2-dimensional (2-d) EOS model which was recently proposed in literature. The 2-d model is found to exhibit significant parameter-estimation biases as more GW events are analyzed, while the predicted $m$-$\Lambda$ relation remains consistent with the full model., Comment: 18 pages, 4 figures

The high-pressure transportation process of pipeline necessitates an accurate hydraulic transient simulation tool to prevent slack line flow and over-pressure, which can endanger pipeline operations. However, current numerical solution methods often face difficulties in balancing computational efficiency and accuracy. Additionally, few studies attempt to reform physics-informed learning architecture for pipeline transient simulation with magnitude different in outputs and imbalanced gradient in loss function. To address these challenges, a Knowledge-Inspired Hierarchical Physics-Informed Neural Network is proposed for hydraulic transient simulation of multi-product pipelines. The proposed model integrates governing equations, boundary conditions, and initial conditions into the training process to ensure consistency with physical laws. Furthermore, magnitude conversion of outputs and equivalent conversion of governing equations are implemented to enhance the training performance of the neural network. To further address the imbalanced gradient of multiple loss terms with fixed weights, a hierarchical training strategy is designed. Numerical simulations demonstrate that the proposed model outperforms state-of-the-art models and can still produce accurate simulation results under complex hydraulic transient conditions, with mean absolute percentage errors reduced by 87.8\% and 92.7 \% in pressure prediction. Thus, the proposed model can conduct accurate and effective hydraulic transient analysis, ensuring the safe operation of pipelines., Comment: 11 pages, 8 figures

This paper pioneers the use of quantum machine learning (QML) for modeling the Ohmic contact process in GaN high-electron-mobility transistors (HEMTs) for the first time. Utilizing data from 159 devices and variational auto-encoder-based augmentation, we developed a quantum kernel-based regressor (QKR) with a 2-level ZZ-feature map. Benchmarking against six classical machine learning (CML) models, our QKR consistently demonstrated the lowest mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE). Repeated statistical analysis confirmed its robustness. Additionally, experiments verified an MAE of 0.314 ohm-mm, underscoring the QKR's superior performance and potential for semiconductor applications, and demonstrating significant advancements over traditional CML methods., Comment: This is the manuscript in the conference version. An expanded version for the journal will be released later and more information will be added. The author list, content, conclusion, and figures may change due to further research

We consider the Cauchy problem to the 3D fractional Schr\"odinger equation with quadratic interaction of $u\bar u$ type. We prove the global existence of solutions and scattering properties for small initial data. For the proof, one novelty is that we combine the normal form methods and the space-time resonance methods. Using the normal form transform enables us more flexibilities in designing the resolution spaces so that we can control various interactions. It is also convenient for the final data problem.

Machine Learning as a Service (MLaaS) is often provided as a pay-per-query, black-box system to clients. Such a black-box approach not only hinders open replication, validation, and interpretation of model results, but also makes it harder for white-hat researchers to identify vulnerabilities in the MLaaS systems. Model extraction is a promising technique to address these challenges by reverse-engineering black-box models. Since training data is typically unavailable for MLaaS models, this paper focuses on the realistic version of it: data-free model extraction. We propose a data-free model extraction approach, CaBaGe, to achieve higher model extraction accuracy with a small number of queries. Our innovations include (1) a novel experience replay for focusing on difficult training samples; (2) an ensemble of generators for steadily producing diverse synthetic data; and (3) a selective filtering process for querying the victim model with harder, more balanced samples. In addition, we create a more realistic setting, for the first time, where the attacker has no knowledge of the number of classes in the victim training data, and create a solution to learn the number of classes on the fly. Our evaluation shows that CaBaGe outperforms existing techniques on seven datasets -- MNIST, FMNIST, SVHN, CIFAR-10, CIFAR-100, ImageNet-subset, and Tiny ImageNet -- with an accuracy improvement of the extracted models by up to 43.13%. Furthermore, the number of queries required to extract a clone model matching the final accuracy of prior work is reduced by up to 75.7%.

Camera-to-robot calibration is crucial for vision-based robot control and requires effort to make it accurate. Recent advancements in markerless pose estimation methods have eliminated the need for time-consuming physical setups for camera-to-robot calibration. While the existing markerless pose estimation methods have demonstrated impressive accuracy without the need for cumbersome setups, they rely on the assumption that all the robot joints are visible within the camera's field of view. However, in practice, robots usually move in and out of view, and some portion of the robot may stay out-of-frame during the whole manipulation task due to real-world constraints, leading to a lack of sufficient visual features and subsequent failure of these approaches. To address this challenge and enhance the applicability to vision-based robot control, we propose a novel framework capable of estimating the robot pose with partially visible robot manipulators. Our approach leverages the Vision-Language Models for fine-grained robot components detection, and integrates it into a keypoint-based pose estimation network, which enables more robust performance in varied operational conditions. The framework is evaluated on both public robot datasets and self-collected partial-view datasets to demonstrate our robustness and generalizability. As a result, this method is effective for robot pose estimation in a wider range of real-world manipulation scenarios., Comment: 7 pages, 5 figures, project website: https://sites.google.com/ucsd.edu/ctrnet-x

Catching objects in flight (i.e., thrown objects) is a common daily skill for humans, yet it presents a significant challenge for robots. This task requires a robot with agile and accurate motion, a large spatial workspace, and the ability to interact with diverse objects. In this paper, we build a mobile manipulator composed of a mobile base, a 6-DoF arm, and a 12-DoF dexterous hand to tackle such a challenging task. We propose a two-stage reinforcement learning framework to efficiently train a whole-body-control catching policy for this high-DoF system in simulation. The objects' throwing configurations, shapes, and sizes are randomized during training to enhance policy adaptivity to various trajectories and object characteristics in flight. The results show that our trained policy catches diverse objects with randomly thrown trajectories, at a high success rate of about 80\% in simulation, with a significant improvement over the baselines. The policy trained in simulation can be directly deployed in the real world with onboard sensing and computation, which achieves catching sandbags in various shapes, randomly thrown by humans. Our project page is available at https://mobile-dex-catch.github.io/.

This letter presents a model to address the collaborative effects in multi-agent systems from the perspective of microscopic mechanism. The model utilizes distributed control for robot swarms in traversal applications. Inspired by pedestrian planning dynamics, the model employs three types of forces to regulate the behavior of agents: intrinsic propulsion, interaction among agents, and repulsion from obstacles. These forces are able to balance the convergence, divergence and avoidance effects among agents. Additionally, we present a planning and decision method based on resultant forces to enable real-world deployment of the model. Experimental results demonstrate the effectiveness on system path optimization in unknown cluttered environments. The sensor data is swiftly digital filtered and the data transmitted is significantly compressed. Consequently, the model has low computation costs and minimal communication loads, thereby promoting environmental adaptability and system scalability., Comment: 8 pages, 8 figures

Financial fraud refers to the act of obtaining financial benefits through dishonest means. Such behavior not only disrupts the order of the financial market but also harms economic and social development and breeds other illegal and criminal activities. With the popularization of the internet and online payment methods, many fraudulent activities and money laundering behaviors in life have shifted from offline to online, posing a great challenge to regulatory authorities. How to efficiently detect these financial fraud activities has become an urgent issue that needs to be resolved. Graph neural networks are a type of deep learning model that can utilize the interactive relationships within graph structures, and they have been widely applied in the field of fraud detection. However, there are still some issues. First, fraudulent activities only account for a very small part of transaction transfers, leading to an inevitable problem of label imbalance in fraud detection. At the same time, fraudsters often disguise their behavior, which can have a negative impact on the final prediction results. In addition, existing research has overlooked the importance of balancing neighbor information and central node information. For example, when the central node has too many neighbors, the features of the central node itself are often neglected. Finally, fraud activities and patterns are constantly changing over time, so considering the dynamic evolution of graph edge relationships is also very important.

This paper considers the generalized maximal covering location problem (GMCLP) which establishes a fixed number of facilities to maximize the weighted sum of the covered customers, allowing customers' weights to be positive or negative. The GMCLP can be modeled as a mixed integer programming (MIP) formulation and solved by off-the-shelf MIP solvers. However, due to the large problem size and particularly, poor linear programming (LP) relaxation, the GMCLP is extremely difficult to solve by state-of-the-art MIP solvers. To improve the computational performance of MIP-based approaches for solving GMCLPs, we propose customized presolving and cutting plane techniques, which are the isomorphic aggregation, dominance reduction, and two-customer inequalities. The isomorphic aggregation and dominance reduction can not only reduce the problem size but also strengthen the LP relaxation of the MIP formulation of the GMCLP. The two-customer inequalities can be embedded into a branch-and-cut framework to further strengthen the LP relaxation of the MIP formulation on the fly. By extensive computational experiments, we show that all three proposed techniques can substantially improve the capability of MIP solvers in solving GMCLPs. In particular, for a testbed of 40 instances with identical numbers of customers and facilities in the literature, the proposed techniques enable to provide optimal solutions for 13 previously unsolved benchmark instances; for a testbed of 56 instances where the number of customers is much larger than the number of facilities, the proposed techniques can turn most of them from intractable to easily solvable., Comment: 25 pages, 10 figures, submitted for possible publication

This paper presents Range-SLAM, a real-time, lightweight SLAM system designed to address the challenges of localization and mapping in environments with smoke and other harsh conditions using Ultra-Wideband (UWB) signals. While optical sensors like LiDAR and cameras struggle in low-visibility environments, UWB signals provide a robust alternative for real-time positioning. The proposed system uses general UWB devices to achieve accurate mapping and localization without relying on expensive LiDAR or other dedicated hardware. By utilizing only the distance and Received Signal Strength Indicator (RSSI) provided by UWB sensors in relation to anchors, we combine the motion of the tag-carrying agent with raycasting algorithm to construct a 2D occupancy grid map in real time. To enhance localization in challenging conditions, a Weighted Least Squares (WLS) method is employed. Extensive real-world experiments, including smoke-filled environments and simulated

Labelled data are limited and self-supervised learning is one of the most important approaches for reducing labelling requirements. While it has been extensively explored in the image domain, it has so far not received the same amount of attention in the acoustic domain. Yet, reducing labelling is a key requirement for many acoustic applications. Specifically in bioacoustic, there are rarely sufficient labels for fully supervised learning available. This has led to the widespread use of acoustic recognisers that have been pre-trained on unrelated data for bioacoustic tasks. We posit that training on the actual task data and combining self-supervised pre-training with few-shot classification is a superior approach that has the ability to deliver high accuracy even when only a few labels are available. To this end, we introduce and evaluate a new architecture that combines CNN-based preprocessing with feature extraction based on state space models (SSMs). This combination is motivated by the fact that CNN-based networks alone struggle to capture temporal information effectively, which is crucial for classifying acoustic signals. SSMs, specifically S4 and Mamba, on the other hand, have been shown to have an excellent ability to capture long-range dependencies in sequence data. We pre-train this architecture using contrastive learning on the actual task data and subsequent fine-tuning with an extremely small amount of labelled data. We evaluate the performance of this proposed architecture for ($n$-shot, $n$-class) classification on standard benchmarks as well as real-world data. Our evaluation shows that it outperforms state-of-the-art architectures on the few-shot classification problem.

Current Pose-Guided Person Image Synthesis (PGPIS) methods depend heavily on large amounts of labeled triplet data to train the generator in a supervised manner. However, they often falter when applied to in-the-wild samples, primarily due to the distribution gap between the training datasets and real-world test samples. While some researchers aim to enhance model generalizability through sophisticated training procedures, advanced architectures, or by creating more diverse datasets, we adopt the test-time fine-tuning paradigm to customize a pre-trained Text2Image (T2I) model. However, naively applying test-time tuning results in inconsistencies in facial identities and appearance attributes. To address this, we introduce a Visual Consistency Module (VCM), which enhances appearance consistency by combining the face, text, and image embedding. Our approach, named OnePoseTrans, requires only a single source image to generate high-quality pose transfer results, offering greater stability than state-of-the-art data-driven methods. For each test case, OnePoseTrans customizes a model in around 48 seconds with an NVIDIA V100 GPU.

The non-uniform current distribution arisen from either current crowding effect or hot spot effect provides a method to tailor the interaction between thermal gradient and electron transport in magnetically ordered systems. Here we apply the device structural engineering to realize an in-plane inhomogeneous temperature distribution within the conduction channel, and the resulting geometric anomalous Nernst effect (GANE) gives rise to a non-zero 2nd -harmonic resistance whose polarity corresponds to the out-of-plane magnetization of Co/Pt multi-layer thin film, and its amplitude is linearly proportional to the applied current. By optimizing the aspect ratio of convex-shaped device, the effective temperature gradient can reach up to 0.3 K/$\mu$m along the y-direction, leading to a GANE signal of 28.3 $\mu$V. Moreover, we demonstrate electrical write and read operations in the perpendicularly-magnetized Co/Pt-based spin-orbit torque device with a simple two-terminal structure. Our results unveil a new pathway to utilize thermoelectric effects for constructing high-density magnetic memories

Previously, a synchrotron-based horizontal proton beamline (87.2 MeV) was successfully commissioned to deliver radiation doses in FLASH and conventional dose rate modes to small fields and volumes. In this study, we developed a strategy to increase the effective radiation field size using a custom robotic motion platform to automatically shift the positions of biological samples. The beam was first broadened with a thin tungsten scatterer and shaped by customized brass collimators for irradiating cell/organoid cultures in 96-well plates (a 7-mm-diameter circle) or for irradiating mice (1-cm2 square). Motion patterns of the robotic platform were written in G-code, with 9-mm spot spacing used for the 96-well plates and 10.6-mm spacing for the mice. The accuracy of target positioning was verified with a self-leveling laser system. The dose delivered in the experimental conditions was validated with EBT-XD film attached to the 96-well plate or the back of the mouse. Our film-measured dose profiles matched Monte Carlo calculations well (1D gamma pass rate >95%). The FLASH dose rates were 113.7 Gy/s for cell/organoid irradiation and 191.3 Gy/s for mouse irradiation. These promising results indicate that this robotic platform can be used to effectively increase the field size for preclinical experiments with proton FLASH.

In this paper, we provide a presentation of the Kauffman bracket skein module for each small Seifert manifold. As one application, we demonstrate how to get the Kauffman bracket skein module of lens spaces from our main theorem., Comment: 14 pages, 13 figures

We introduce Diffusion-based Audio Captioning (DAC), a non-autoregressive diffusion model tailored for diverse and efficient audio captioning. Although existing captioning models relying on language backbones have achieved remarkable success in various captioning tasks, their insufficient performance in terms of generation speed and diversity impede progress in audio understanding and multimedia applications. Our diffusion-based framework offers unique advantages stemming from its inherent stochasticity and holistic context modeling in captioning. Through rigorous evaluation, we demonstrate that DAC not only achieves SOTA performance levels compared to existing benchmarks in the caption quality, but also significantly outperforms them in terms of generation speed and diversity. The success of DAC illustrates that text generation can also be seamlessly integrated with audio and visual generation tasks using a diffusion backbone, paving the way for a unified, audio-related generative model across different modalities., Comment: https://sites.google.com/view/diffusion-audio-captioning

The Matrix Profile (MP), a versatile tool for time series data mining, has been shown effective in time series anomaly detection (TSAD). This paper delves into the problem of anomaly detection in multidimensional time series, a common occurrence in real-world applications. For instance, in a manufacturing factory, multiple sensors installed across the site collect time-varying data for analysis. The Matrix Profile, named for its role in profiling the matrix storing pairwise distance between subsequences of univariate time series, becomes complex in multidimensional scenarios. If the input univariate time series has n subsequences, the pairwise distance matrix is a n x n matrix. In a multidimensional time series with d dimensions, the pairwise distance information must be stored in a n x n x d tensor. In this paper, we first analyze different strategies for condensing this tensor into a profile vector. We then investigate the potential of extending the MP to efficiently find k-nearest neighbors for anomaly detection. Finally, we benchmark the multidimensional MP against 19 baseline methods on 119 multidimensional TSAD datasets. The experiments covers three learning setups: unsupervised, supervised, and semi-supervised. MP is the only method that consistently delivers high performance across all setups.

Dynamic and dexterous manipulation of objects presents a complex challenge, requiring the synchronization of hand motions with the trajectories of objects to achieve seamless and physically plausible interactions. In this work, we introduce ManiDext, a unified hierarchical diffusion-based framework for generating hand manipulation and grasp poses based on 3D object trajectories. Our key insight is that accurately modeling the contact correspondences between objects and hands during interactions is crucial. Therefore, we propose a continuous correspondence embedding representation that specifies detailed hand correspondences at the vertex level between the object and the hand. This embedding is optimized directly on the hand mesh in a self-supervised manner, with the distance between embeddings reflecting the geodesic distance. Our framework first generates contact maps and correspondence embeddings on the object's surface. Based on these fine-grained correspondences, we introduce a novel approach that integrates the iterative refinement process into the diffusion process during the second stage of hand pose generation. At each step of the denoising process, we incorporate the current hand pose residual as a refinement target into the network, guiding the network to correct inaccurate hand poses. Introducing residuals into each denoising step inherently aligns with traditional optimization process, effectively merging generation and refinement into a single unified framework. Extensive experiments demonstrate that our approach can generate physically plausible and highly realistic motions for various tasks, including single and bimanual hand grasping as well as manipulating both rigid and articulated objects. Code will be available for research purposes.

Multi-object tracking (MOT) emerges as a pivotal and highly promising branch in the field of computer vision. Classical closed-vocabulary MOT (CV-MOT) methods aim to track objects of predefined categories. Recently, some open-vocabulary MOT (OV-MOT) methods have successfully addressed the problem of tracking unknown categories. However, we found that the CV-MOT and OV-MOT methods each struggle to excel in the tasks of the other. In this paper, we present a unified framework, Associate Everything Detected (AED), that simultaneously tackles CV-MOT and OV-MOT by integrating with any off-the-shelf detector and supports unknown categories. Different from existing tracking-by-detection MOT methods, AED gets rid of prior knowledge (e.g. motion cues) and relies solely on highly robust feature learning to handle complex trajectories in OV-MOT tasks while keeping excellent performance in CV-MOT tasks. Specifically, we model the association task as a similarity decoding problem and propose a sim-decoder with an association-centric learning mechanism. The sim-decoder calculates similarities in three aspects: spatial, temporal, and cross-clip. Subsequently, association-centric learning leverages these threefold similarities to ensure that the extracted features are appropriate for continuous tracking and robust enough to generalize to unknown categories. Compared with existing powerful OV-MOT and CV-MOT methods, AED achieves superior performance on TAO, SportsMOT, and DanceTrack without any prior knowledge. Our code is available at https://github.com/balabooooo/AED.

In social networks or spatial experiments, one unit's outcome often depends on another's treatment, a phenomenon called interference. Researchers are interested in not only the presence and magnitude of interference but also its pattern based on factors like distance, neighboring units, and connection strength. However, the non-random nature of these factors and complex correlations across units pose challenges for inference. This paper introduces the partial null randomization tests (PNRT) framework to address these issues. The proposed method is finite-sample valid and applicable with minimal network structure assumptions, utilizing randomization testing and pairwise comparisons. Unlike existing conditional randomization tests, PNRT avoids the need for conditioning events, making it more straightforward to implement. Simulations demonstrate the method's desirable power properties and its applicability to general interference scenarios.

Language models (LMs) are revolutionizing knowledge retrieval and processing in academia. However, concerns regarding their misuse and erroneous outputs, such as hallucinations and fabrications, are reasons for distrust in LMs within academic communities. Consequently, there is a pressing need to deepen the understanding of how actual practitioners use and trust these models. There is a notable gap in quantitative evidence regarding the extent of LM usage, user trust in their outputs, and issues to prioritize for real-world development. This study addresses these gaps by providing data and analysis of LM usage and trust. Specifically, our study surveyed 125 individuals at a private school and secured 88 data points after pre-processing. Through both quantitative analysis and qualitative evidence, we found a significant variation in trust levels, which are strongly related to usage time and frequency. Additionally, we discover through a polling process that fact-checking is the most critical issue limiting usage. These findings inform several actionable insights: distrust can be overcome by providing exposure to the models, policies should be developed that prioritize fact-checking, and user trust can be enhanced by increasing engagement. By addressing these critical gaps, this research not only adds to the understanding of user experiences and trust in LMs but also informs the development of more effective LMs.

Synthesizable molecular design (also known as synthesizable molecular optimization) is a fundamental problem in drug discovery, and involves designing novel molecular structures to improve their properties according to drug-relevant oracle functions (i.e., objective) while ensuring synthetic feasibility. However, existing methods are mostly based on random search. To address this issue, in this paper, we introduce a novel approach using the reinforcement learning method with quantum-inspired simulated annealing policy neural network to navigate the vast discrete space of chemical structures intelligently. Specifically, we employ a deterministic REINFORCE algorithm using policy neural networks to output transitional probability to guide state transitions and local search using genetic algorithm to refine solutions to a local optimum within each iteration. Our methods are evaluated with the Practical Molecular Optimization (PMO) benchmark framework with a 10K query budget. We further showcase the competitive performance of our method by comparing it against the state-of-the-art genetic algorithms-based method.

Accurate imputation is essential for the reliability and success of downstream tasks. Recently, diffusion models have attracted great attention in this field. However, these models neglect the latent distribution in a lower-dimensional space derived from the observed data, which limits the generative capacity of the diffusion model. Additionally, dealing with the original missing data without labels becomes particularly problematic. To address these issues, we propose the Latent Space Score-Based Diffusion Model (LSSDM) for probabilistic multivariate time series imputation. Observed values are projected onto low-dimensional latent space and coarse values of the missing data are reconstructed without knowing their ground truth values by this unsupervised learning approach. Finally, the reconstructed values are fed into a conditional diffusion model to obtain the precise imputed values of the time series. In this way, LSSDM not only possesses the power to identify the latent distribution but also seamlessly integrates the diffusion model to obtain the high-fidelity imputed values and assess the uncertainty of the dataset. Experimental results demonstrate that LSSDM achieves superior imputation performance while also providing a better explanation and uncertainty analysis of the imputation mechanism. The website of the code is \textit{https://github.com/gorgen2020/LSSDM\_imputation}., Comment: 5 pages, conference

We employ the entropic uncertainty relations and the quantum Fisher information to explore the formation of quark $t\bar{t}$ pairs at a large hadron collider through the combination of $q\bar{q}$ pair and $gg$ pair initiated processes. A comprehensive analysis has been undertaken on the procedure of quark and gluon channel mixing in the production of top quark pairs $t\bar{t}$, encompassing the tightness of the entropic uncertainty inequalities and the maximum quantum Fisher information of the system., Comment: 15 pages, 11 figures

The planar two-loop scalar Feynman integrals contributing to the massive NNLO QCD corrections for $W$-boson pair production via quark-antiquark annihilation can be classified into three family branches, each of which is reduced to a distinct set of master integrals (MIs), totaling $27$, $45$ and $15$, respectively. These MIs are analytically calculated using the method of differential equations, with solutions expanded as Taylor series in the dimensional regulator $\epsilon$. For the first two family branches, the differential systems can be successfully transformed into canonical form by adopting appropriate bases of MIs. This enables the MIs of these family branches to be expressed either as Goncharov polylogarithms (GPLs) or as one-fold integrals over GPLs, up to $\mathcal{O}(\epsilon^4)$. In contrast, the differential system for the third family branch can only be cast into a form linear in $\epsilon$ due to the presence of elliptic integrals. The solution to this linear-form differential system is expressed in an iterated form owing to the strictly lower-triangular structure of the coefficient matrices at $\epsilon = 0$. Our analytic expressions for these MIs are verified with high accuracy against the numerical results from the \texttt{AMFlow} package., Comment: 39 pages, 4 figures

The XENONnT experiment, located at the INFN Laboratori Nazionali del Gran Sasso, Italy, features a 5.9 tonne liquid xenon time projection chamber surrounded by an instrumented neutron veto, all of which is housed within a muon veto water tank. Due to extensive shielding and advanced purification to mitigate natural radioactivity, an exceptionally low background level of (15.8 $\pm$ 1.3) events/(tonne$\cdot$year$\cdot$keV) in the (1, 30) keV region is reached in the inner part of the TPC. XENONnT is thus sensitive to a wide range of rare phenomena related to Dark Matter and Neutrino interactions, both within and beyond the Standard Model of particle physics, with a focus on the direct detection of Dark Matter in the form of weakly interacting massive particles (WIMPs). From May 2021 to December 2021, XENONnT accumulated data in rare-event search mode with a total exposure of one tonne $\cdot$ year. This paper provides a detailed description of the signal reconstruction methods, event selection procedure, and detector response calibration, as well as an overview of the detector performance in this time frame. This work establishes the foundational framework for the `blind analysis' methodology we are using when reporting XENONnT physics results., Comment: 27 pages, 23 figures

Visual and auditory perception are two crucial ways humans experience the world. Text-to-video generation has made remarkable progress over the past year, but the absence of harmonious audio in generated video limits its broader applications. In this paper, we propose Semantic and Temporal Aligned Video-to-Audio (STA-V2A), an approach that enhances audio generation from videos by extracting both local temporal and global semantic video features and combining these refined video features with text as cross-modal guidance. To address the issue of information redundancy in videos, we propose an onset prediction pretext task for local temporal feature extraction and an attentive pooling module for global semantic feature extraction. To supplement the insufficient semantic information in videos, we propose a Latent Diffusion Model with Text-to-Audio priors initialization and cross-modal guidance. We also introduce Audio-Audio Align, a new metric to assess audio-temporal alignment. Subjective and objective metrics demonstrate that our method surpasses existing Video-to-Audio models in generating audio with better quality, semantic consistency, and temporal alignment. The ablation experiment validated the effectiveness of each module. Audio samples are available at https://y-ren16.github.io/STAV2A., Comment: Submitted to ICASSP2025

Dynamic MR images possess various transformation symmetries,including the rotation symmetry of local features within the image and along the temporal dimension. Utilizing these symmetries as prior knowledge can facilitate dynamic MR imaging with high spatiotemporal resolution. Equivariant CNN is an effective tool to leverage the symmetry priors. However, current equivariant CNN methods fail to fully exploit these symmetry priors in dynamic MR imaging. In this work, we propose a novel framework of Spatiotemporal Rotation-Equivariant CNN (SRE-CNN), spanning from the underlying high-precision filter design to the construction of the temporal-equivariant convolutional module and imaging model, to fully harness the rotation symmetries inherent in dynamic MR images. The temporal-equivariant convolutional module enables exploitation the rotation symmetries in both spatial and temporal dimensions, while the high-precision convolutional filter, based on parametrization strategy, enhances the utilization of rotation symmetry of local features to improve the reconstruction of detailed anatomical structures. Experiments conducted on highly undersampled dynamic cardiac cine data (up to 20X) have demonstrated the superior performance of our proposed approach, both quantitatively and qualitatively., Comment: Accepted at MICCAI 2024

Wake and force characteristics of an oscillating cylinder in inline steady currents are investigated numerically over a wide parameter space of dimensionless oscillation amplitude ($A^* = 0.01 - 0.50$) and wavelength ($\lambda^* = 0.4 - 25$) at a fixed Reynolds number $Re = 500$. Fundamental issues addressed in this study are the interactions of wakes induced by steady approaching flow and cylinder oscillations and the influences of the governing parameters of $A^$ and $\lambda^$ on such interactions. Whilst the collinear flow is dominated by wakes induced by cylinder oscillation at $\lambda^* \leq 1.5$ and steady current at $\lambda^* \geq 10$, it exhibits characteristics of nonlinear interactions of wakes induced by the cylinder oscillation and steady current at $\lambda^* = 1.5 - 10$, such as the formation of multiple synchronized modes interleaved with desynchronized modes. The synchronized mode varies with both $\lambda^$ and $A^$, forming an inclined Arnold's tongue across $\lambda^-A^$ space. There is a wide variability of the vortex shedding pattern in each synchronized mode. Variations of different hydrodynamic force coefficients with $\lambda^$ and $A^$ are investigated with physical interpretations based on the wake characteristics. The applicability of the Morison equation in predicting inline force fluctuations is examined. We found that the Morison equation shows reasonable accuracy only for a small range of $\lambda^* \leq 1.5$. Beyond this range, its performance deteriorates due to the influence of steady current on wake characteristics., Comment: Under review in JFM

Unsupervised domain adaptation (UDA) of time series aims to teach models to identify consistent patterns across various temporal scenarios, disregarding domain-specific differences, which can maintain their predictive accuracy and effectively adapt to new domains. However, existing UDA methods struggle to adequately extract and align both global and local features in time series data. To address this issue, we propose the Local-Global Representation Alignment framework (LogoRA), which employs a two-branch encoder, comprising a multi-scale convolutional branch and a patching transformer branch. The encoder enables the extraction of both local and global representations from time series. A fusion module is then introduced to integrate these representations, enhancing domain-invariant feature alignment from multi-scale perspectives. To achieve effective alignment, LogoRA employs strategies like invariant feature learning on the source domain, utilizing triplet loss for fine alignment and dynamic time warping-based feature alignment. Additionally, it reduces source-target domain gaps through adversarial training and per-class prototype alignment. Our evaluations on four time-series datasets demonstrate that LogoRA outperforms strong baselines by up to $12.52\%$, showcasing its superiority in time series UDA tasks., Comment: Accepted by IEEE Transactions on Knowledge and Data Engineering

Polarons, quasiparticles arising from electron-phonon coupling, are crucial in understanding material properties such as high-temperature superconductivity and colossal magnetoresistance. However, scarce studies have been performed to investigate the formation of polarons in low-dimensional materials with phonon polarity and electronic structure transitions. In this work, we studied polarons of tellurene that are composed of chiral chains of tellurium atoms. The frequency and linewidth of the A1 phonon, which becomes increasingly polar for thinner tellurene, exhibit an abrupt change when the thickness of tellurene is below 10 nm. Meanwhile, the field effect mobility of tellurene drops rapidly as the thickness is smaller than 10 nm. These phonon and transport signatures, combined with the calculated phonon polarity and band structure, suggest a crossover from large polarons for bulk tellurium to small polarons for few-layer tellurene. Effective field theory considers the phonon renormalization in the strong coupling (small polaron) regime, and semi-quantitatively reproduces the observed phonon hardening and broadening effects in few-layer tellurene. This polaron crossover stems from the quasi-1D nature of tellurene where modulation of the interchain distance reduces the dielectric screening and promotes electron-phonon coupling. Our work provides valuable insights into the influence of polarons on phononic, electronic, and structural properties in low-dimensional materials.

The past few centuries have witnessed a dramatic growth in scientific and technological knowledge. However, the nature of that growth - whether exponential or otherwise - remains controversial, perhaps partly due to the lack of quantitative characterizations. We evaluated knowledge as a collective thinking structure, using citation networks as a representation, by examining extensive datasets that include 213 million publications (1800-2020) and 7.6 million patents (1976-2020). We found that knowledge - which we conceptualize as the reduction of uncertainty in a knowledge network - grew linearly over time in naturally formed citation networks that themselves expanded exponentially. Moreover, our results revealed inflection points in the growth of knowledge that often corresponded to important developments within fields, such as major breakthroughs, new paradigms, or the emergence of entirely new areas of study. Around these inflection points, knowledge may grow rapidly or exponentially on a local scale, although the overall growth rate remains linear when viewed globally. Previous studies concluding an exponential growth of knowledge may have focused primarily on these local bursts of rapid growth around key developments, leading to the misconception of a global exponential trend. Our findings help to reconcile the discrepancy between the perceived exponential growth and the actual linear growth of knowledge by highlighting the distinction between local and global growth patterns. Overall, our findings reveal major science development trends for policymaking, showing that producing knowledge is far more challenging than producing papers.

Music is inherently made up of complex structures, and representing them as graphs helps to capture multiple levels of relationships. While music generation has been explored using various deep generation techniques, research on graph-related music generation is sparse. Earlier graph-based music generation worked only on generating melodies, and recent works to generate polyphonic music do not account for longer-term structure. In this paper, we explore a multi-graph approach to represent both the rhythmic patterns and phrase structure of Chinese pop music. Consequently, we propose a two-step approach that aims to generate polyphonic music with coherent rhythm and long-term structure. We train two Variational Auto-Encoder networks - one on a MIDI dataset to generate 4-bar phrases, and another on song structure labels to generate full song structure. Our work shows that the models are able to learn most of the structural nuances in the training dataset, including chord and pitch frequency distributions, and phrase attributes.

Controllable magnetization in atomically thin two-dimensional magnets is highly desirable for developing spintronics. For FeSe monolayer, its magnetic ground state is not yet fully understood, and the potential in constructing high-speed and advanced devices remains unknown. Using density functional theory calculations, we confirm the spin ordering of monolayer FeSe to be dimer texture. With Fluorine (F) adsorption (F/FeSe), the system exhibits a coverage dependent magnetic anisotropy and multiferroicity which can be attributable to the Jahn-Teller effect, being the benefit to potential spintronic applications. Intriguingly, an inherent coupling between magnetism and ferroelasticity in the most energetically favorable F/FeSe system is proposed. Our study thus not only provides a promising way to control the spintronic properties and construct multiferroics, but also renders F/FeSe an ideal platform for magnetism studies and practical high-performance multifunctional devices., Comment: 13 pages, 5 figures

In the domain of human-computer interaction, accurately recognizing and interpreting human emotions is crucial yet challenging due to the complexity and subtlety of emotional expressions. This study explores the potential for detecting a rich and flexible range of emotions through a multimodal approach which integrates facial expressions, voice tones, and transcript from video clips. We propose a novel framework that maps variety of emotions in a three-dimensional Valence-Arousal-Dominance (VAD) space, which could reflect the fluctuations and positivity/negativity of emotions to enable a more variety and comprehensive representation of emotional states. We employed K-means clustering to transit emotions from traditional discrete categorization to a continuous labeling system and built a classifier for emotion recognition upon this system. The effectiveness of the proposed model is evaluated using the MER2024 dataset, which contains culturally consistent video clips from Chinese movies and TV series, annotated with both discrete and open-vocabulary emotion labels. Our experiment successfully achieved the transformation between discrete and continuous models, and the proposed model generated a more diverse and comprehensive set of emotion vocabulary while maintaining strong accuracy.

UI automation tests play a crucial role in ensuring the quality of mobile applications. Despite the growing popularity of machine learning techniques to generate these tests, they still face several challenges, such as the mismatch of UI elements. The recent advances in Large Language Models (LLMs) have addressed these issues by leveraging their semantic understanding capabilities. However, a significant gap remains in applying these models to industrial-level app testing, particularly in terms of cost optimization and knowledge limitation. To address this, we introduce CAT to create cost-effective UI automation tests for industry apps by combining machine learning and LLMs with best practices. Given the task description, CAT employs Retrieval Augmented Generation (RAG) to source examples of industrial app usage as the few-shot learning context, assisting LLMs in generating the specific sequence of actions. CAT then employs machine learning techniques, with LLMs serving as a complementary optimizer, to map the target element on the UI screen. Our evaluations on the WeChat testing dataset demonstrate the CAT's performance and cost-effectiveness, achieving 90% UI automation with $0.34 cost, outperforming the state-of-the-art. We have also integrated our approach into the real-world WeChat testing platform, demonstrating its usefulness in detecting 141 bugs and enhancing the developers' testing process.

Rapid advancements in artificial intelligence have significantly enhanced generative tasks involving music and images, employing both unimodal and multimodal approaches. This research develops a model capable of generating music that resonates with the emotions depicted in visual arts, integrating emotion labeling, image captioning, and language models to transform visual inputs into musical compositions. Addressing the scarcity of aligned art and music data, we curated the Emotion Painting Music Dataset, pairing paintings with corresponding music for effective training and evaluation. Our dual-stage framework converts images to text descriptions of emotional content and then transforms these descriptions into music, facilitating efficient learning with minimal data. Performance is evaluated using metrics such as Fr\'echet Audio Distance (FAD), Total Harmonic Distortion (THD), Inception Score (IS), and KL divergence, with audio-emotion text similarity confirmed by the pre-trained CLAP model to demonstrate high alignment between generated music and text. This synthesis tool bridges visual art and music, enhancing accessibility for the visually impaired and opening avenues in educational and therapeutic applications by providing enriched multi-sensory experiences.

This paper introduces GateAttentionPose, an innovative approach that enhances the UniRepLKNet architecture for pose estimation tasks. We present two key contributions: the Agent Attention module and the Gate-Enhanced Feedforward Block (GEFB). The Agent Attention module replaces large kernel convolutions, significantly improving computational efficiency while preserving global context modeling. The GEFB augments feature extraction and processing capabilities, particularly in complex scenes. Extensive evaluations on COCO and MPII datasets demonstrate that GateAttentionPose outperforms existing state-of-the-art methods, including the original UniRepLKNet, achieving superior or comparable results with improved efficiency. Our approach offers a robust solution for pose estimation across diverse applications, including autonomous driving, human motion capture, and virtual reality.

Federated recommender systems (FedRecs) have emerged as a popular research direction for protecting users' privacy in on-device recommendations. In FedRecs, users keep their data locally and only contribute their local collaborative information by uploading model parameters to a central server. While this rigid framework protects users' raw data during training, it severely compromises the recommendation model's performance due to the following reasons: (1) Due to the power law distribution nature of user behavior data, individual users have few data points to train a recommendation model, resulting in uploaded model updates that may be far from optimal; (2) As each user's uploaded parameters are learned from local data, which lacks global collaborative information, relying solely on parameter aggregation methods such as FedAvg to fuse global collaborative information may be suboptimal. To bridge this performance gap, we propose a novel federated recommendation framework, PDC-FRS. Specifically, we design a privacy-preserving data contribution mechanism that allows users to share their data with a differential privacy guarantee. Based on the shared but perturbed data, an auxiliary model is trained in parallel with the original federated recommendation process. This auxiliary model enhances FedRec by augmenting each user's local dataset and integrating global collaborative information. To demonstrate the effectiveness of PDC-FRS, we conduct extensive experiments on two widely used recommendation datasets. The empirical results showcase the superiority of PDC-FRS compared to baseline methods.