Searcharxiv⌕ Search

arXiv subjects

Xin Tang

Publications and source records attributed to Xin Tang.

At least 37 records · Page 2Linked to original sources
arXiv2025

The Homework Wars: Exploring Emotions, Behaviours, and Conflicts in Parent-Child Homework Interactions

Parental involvement in homework is a crucial aspect of family education, but it often triggers emotional strain and conflicts. Despite growing concern over its impact on family well-being, prior research has lacked access to fine-grained, real-time dynamics of these interactions. To bridge this gap, we present a framework that leverages naturalistic parent-child interaction data and large language models (LLMs) to analyse homework conversations at scale. In a four-week in situ study with 78 Chinese families, we collected 475 hours of audio recordings and accompanying daily surveys, capturing 602 homework sessions in everyday home settings. Our LLM-based pipeline reliably extracted and categorised parental behaviours and conflict patterns from transcribed conversations, achieving high agreement with expert annotations. The analysis revealed significant emotional shifts in parents before and after homework, 18 recurring parental behaviours and seven common conflict types, with Knowledge Conflict being the most frequent. Notably, even well-intentioned behaviours were significantly positively correlated with specific conflicts. This work advances ubiquitous computing methods for studying complex family dynamics and offers empirical insights to enrich family education theory and inform more effective parenting strategies and interventions in the future.

cs.HC↗
arXiv2025

Task Assignment and Exploration Optimization for Low Altitude UAV Rescue via Generative AI Enhanced Multi-agent Reinforcement Learning

The integration of emerging uncrewed aerial vehicles (UAVs) with artificial intelligence (AI) and ground-embedded robots (GERs) has transformed emergency rescue operations in unknown environments. However, the high computational demands often exceed a single UAV's capacity, making it difficult to continuously provide stable high-level services. To address this, this paper proposes a cooperation framework involving UAVs, GERs, and airships. The framework enables resource pooling through UAV-to-GER (U2G) and UAV-to-airship (U2A) links, offering computing services for offloaded tasks. Specifically, we formulate the multi-objective problem of task assignment and exploration as a dynamic long-term optimization problem aiming to minimize task completion time and energy use while ensuring stability. Using Lyapunov optimization, we transform it into a per-slot deterministic problem and propose HG-MADDPG, which combines the Hungarian algorithm with a GDM-based multi-agent deep deterministic policy gradient. Simulations demonstrate significant improvements in offloading efficiency, latency, and system stability over baselines.

cs.AI↗
arXiv2025

An independent estimate of H(z) at z = 0.5 from the stellar ages of brightest cluster galaxies

Several cosmological observations (e.g., Cosmic Microwave Background (CMB), Supernovae Type Ia, and local distance ladder measurements such as Cepheids) have been used to measure the global expansion rate of the Universe, i.e., the Hubble constant, $H_{0}$. However, these precision measurements have revealed tensions between different probes that are proving difficult to solve. Independent, robust techniques must be exploited to validate results or mitigate systematic effects. We use the Cosmic Chronometer (CC) method, which leverages the differential age evolution of passive galaxies, to measure $H(z)$, without any assumption of the underlying cosmology. Unlike previous CC studies, we used only brightest cluster galaxies (BCGs), the oldest and most massive galaxies in the Universe, to construct a pure and homogeneous sample. In this work we used a sample of 53 BCGs in massive, Sunyaev-Zel'dovich selected galaxy clusters (0.3 $< z <$ 0.7) with Southern African Large Telescope (SALT) spectroscopic observations. We used optical spectra to measure D4000$_{\rm n}$ of the BCGs to obtain a new direct measurement of $H(z) = 72.1 \pm 33.9(\rm stat) \pm 7.3$(syst) km s$^{-1}$ Mpc$^{-1}$ at $z=0.5$. By using BCGs, we significantly reduced the systematic errors to 10% by minimising the stellar mass and metallicity dependence of the method. The dominant uncertainty, and limitation for our study, is statistical, and we need larger, homogeneous samples of the oldest, most massive galaxies. By using the $Planck$+BAO prior of $Ω_{m}$ and $Ω_Λ$, the projected Hubble constant is $H_{0}$ = $54.6 \pm 25.7(\rm stat) \pm 5.5$(syst) km s$^{-1}$ Mpc$^{-1}$, consistent with both CMB and Cepheid measurements.

astro-ph.CO↗
arXiv2024

DNN Task Assignment in UAV Networks: A Generative AI Enhanced Multi-Agent Reinforcement Learning Approach

Unmanned Aerial Vehicles (UAVs) possess high mobility and flexible deployment capabilities, prompting the development of UAVs for various application scenarios within the Internet of Things (IoT). The unique capabilities of UAVs give rise to increasingly critical and complex tasks in uncertain and potentially harsh environments. The substantial amount of data generated from these applications necessitates processing and analysis through deep neural networks (DNNs). However, UAVs encounter challenges due to their limited computing resources when managing DNN models. This paper presents a joint approach that combines multiple-agent reinforcement learning (MARL) and generative diffusion models (GDM) for assigning DNN tasks to a UAV swarm, aimed at reducing latency from task capture to result output. To address these challenges, we first consider the task size of the target area to be inspected and the shortest flying path as optimization constraints, employing a greedy algorithm to resolve the subproblem with a focus on minimizing the UAV's flying path and the overall system cost. In the second stage, we introduce a novel DNN task assignment algorithm, termed GDM-MADDPG, which utilizes the reverse denoising process of GDM to replace the actor network in multi-agent deep deterministic policy gradient (MADDPG). This approach generates specific DNN task assignment actions based on agents' observations in a dynamic environment. Simulation results indicate that our algorithm performs favorably compared to benchmarks in terms of path planning, Age of Information (AoI), energy consumption, and task load balancing.

cs.AI↗
arXiv2024

Digital Twin-Empowered Task Assignment in Aerial MEC Network: A Resource Coalition Cooperation Approach with Generative Model

To meet the demands for ubiquitous communication and temporary edge computing in 6G networks, aerial mobile edge computing (MEC) networks have been envisioned as a new paradigm. However, dynamic user requests pose challenges for task assignment strategies. Most of the existing research assumes that the strategy is deployed on ground-based stations or UAVs, which will be ineffective in an environment lacking infrastructure and continuous energy supply. Moreover, the resource mutual exclusion problem of dynamic task assignment has not been effectively solved. Toward this end, we introduce the digital twin (DT) into the aerial MEC network to study the resource coalition cooperation approach with the generative model (GM), which provides a preliminary coalition structure for the coalition game. Specifically, we propose a novel network framework that is composed of an application plane, a physical plane, and a virtual plane. After that, the task assignment problem is simplified to convex optimization programming with linear constraints. And then, we also propose a resource coalition cooperation approach that is based on a transferable utility (TU) coalition game to obtain an approximate optimal solution. Numerical results confirm the effectiveness of our proposed approach in terms of energy consumption and utilization of resources.

cs.NI↗
arXiv2024

Constraining Holographic Dark Energy and Analyzing Cosmological Tensions

We investigate cosmological constraints on the holographic dark energy (HDE) using the state-of-the-art cosmological datasets: Planck CMB angular power spectra and weak lensing power spectra, Atacama Cosmology Telescope (ACT) temperature power spectra, baryon acoustic oscillation (BAO) and redshift-space distortion (RSD) measurements from six-degree-field galaxy survey and Sloan Digital Sky Survey (DR12 & DR16) and the Cepheids-Supernovae measurement from SH0ES team (R22). We also examine the HDE model and $Λ$CDM with and without $N_{\rm eff}$ (effective number of relativistic species) being treated as a free parameter. We find that the HDE model can relieve the tensions of $H_0$ and $S_8$ to certain degrees. With ``Planck+ACT+BAO+RSD'' datasets, the constraints are $H_0 = 69.70 \pm 1.39\ \mathrm{km\ s^{-1} Mpc^{-1}}$ and $S_8 = 0.823 \pm 0.011$ in HDE model, which brings down the Hubble tension down to $1.92σ$ confidence level (C.L.) and the $S_8$ tension to $1$-$2σ$ C.L. By adding the R22 data, their values are improved as $H_0 = 71.86 \pm 0.93 \,\mathrm{km\ s^{-1} Mpc^{-1}}$ and $S_8 = 0.813 \pm 0.010$, which further brings the Hubble tension down to $0.85σ$ C.L. and relieves the $S_{8}$ tension. We also quantify the goodness-of-fit of different models with Akaike information criterion (AIC) and Bayesian information criterion (BIC), and find that the HDE agrees with the observational data better than the $Λ$CDM and other extended models (treating $N_{\rm eff}$ as free for fitting).

astro-ph.CO↗
arXiv2024

In-sensor Computing ANN Capacitive Sensors

This letter proposes an in-sensor computing multiply-and-accumulate (MAC) circuit based on capacitance. The MAC circuits can constitute an artificial neural network(ANN) layer and be operated as ANN classifiers and autoencoders. The proposed circuit is a promising scheme for capacitive ANN image sensors, showing competitively high efficiency and lower power.

eess.SP↗
arXiv2023

Filter Pruning via Filters Similarity in Consecutive Layers

Filter pruning is widely adopted to compress and accelerate the Convolutional Neural Networks (CNNs), but most previous works ignore the relationship between filters and channels in different layers. Processing each layer independently fails to utilize the collaborative relationship across layers. In this paper, we intuitively propose a novel pruning method by explicitly leveraging the Filters Similarity in Consecutive Layers (FSCL). FSCL compresses models by pruning filters whose corresponding features are more worthless in the model. The extensive experiments demonstrate the effectiveness of FSCL, and it yields remarkable improvement over state-of-the-art on accuracy, FLOPs and parameter reduction on several benchmark models and datasets.

cs.CV↗
arXiv2023

Stepdown SLOPE for Controlled Feature Selection

Sorted L-One Penalized Estimation (SLOPE) has shown the nice theoretical property as well as empirical behavior recently on the false discovery rate (FDR) control of high-dimensional feature selection by adaptively imposing the non-increasing sequence of tuning parameters on the sorted $\ell_1$ penalties. This paper goes beyond the previous concern limited to the FDR control by considering the stepdown-based SLOPE to control the probability of $k$ or more false rejections ($k$-FWER) and the false discovery proportion (FDP). Two new SLOPEs, called $k$-SLOPE and F-SLOPE, are proposed to realize $k$-FWER and FDP control respectively, where the stepdown procedure is injected into the SLOPE scheme. For the proposed stepdown SLOPEs, we establish their theoretical guarantees on controlling $k$-FWER and FDP under the orthogonal design setting, and also provide an intuitive guideline for the choice of regularization parameter sequence in much general setting. Empirical evaluations on simulated data validate the effectiveness of our approaches on controlled feature selection and support our theoretical findings.

math.ST↗
arXiv2023

Stability-based Generalization Analysis for Mixtures of Pointwise and Pairwise Learning

Recently, some mixture algorithms of pointwise and pairwise learning (PPL) have been formulated by employing the hybrid error metric of "pointwise loss + pairwise loss" and have shown empirical effectiveness on feature selection, ranking and recommendation tasks. However, to the best of our knowledge, the learning theory foundation of PPL has not been touched in the existing works. In this paper, we try to fill this theoretical gap by investigating the generalization properties of PPL. After extending the definitions of algorithmic stability to the PPL setting, we establish the high-probability generalization bounds for uniformly stable PPL algorithms. Moreover, explicit convergence rates of stochastic gradient descent (SGD) and regularized risk minimization (RRM) for PPL are stated by developing the stability analysis technique of pairwise learning. In addition, the refined generalization bounds of PPL are obtained by replacing uniform stability with on-average stability.

cs.LG↗
arXiv2022

In-gap states and strain-tuned band convergence in layered structure trivalent iridate K0.75Na0.25IrO2

Iridium oxides (iridates) provide a good platform to study the delicate interplay between spin-orbit coupling (SOC) interactions, electron correlation effects, Hund's coupling and lattice degree of freedom. However, overwhelming investigations primarily focus on tetravalent (Ir4+, 5d5) and pentavalent (Ir5+, 5d4) iridates, far less attention has been paid to iridates with other valence states. Here, we pay our attention to a less-explored trivalent (Ir3+, 5d6) iridates, K0.75Na0.25IrO2, crystalizing in a triangular lattice with edge-sharing IrO6 octahedra and alkali metal ions intercalated [IrO2]- layers. We theoretically determine the preferred occupied positions of the alkali metal ions from energetic viewpoints and reproduce the experimentally observed semiconducting behavior and nonmagnetic (NM) properties. The SOC interactions play a critical role in the band dispersion, resulting in NM Jeff = 0 states. More intriguingly, our electronic structure not only uncovers the presence of in-gap states and explains the abnormal low activation energy in K0.75Na0.25IrO2, but also predicts the band edge can be effectively modulated by mechanical strain. Especially, the in-gap states feature with enhanced band-convergence characteristics by 6% compressive strain, which will greatly enhance the electrical conductivity of K0.75Na0.25IrO2. Present work sheds new lights on the unconventional electronic structures of the trivalent iridates, indicating its promising application as nanoelectronic and thermoelectric material.

cond-mat.str-el↗
arXiv2022

HCL: Improving Graph Representation with Hierarchical Contrastive Learning

Contrastive learning has emerged as a powerful tool for graph representation learning. However, most contrastive learning methods learn features of graphs with fixed coarse-grained scale, which might underestimate either local or global information. To capture more hierarchical and richer representation, we propose a novel Hierarchical Contrastive Learning (HCL) framework that explicitly learns graph representation in a hierarchical manner. Specifically, HCL includes two key components: a novel adaptive Learning to Pool (L2Pool) method to construct more reasonable multi-scale graph topology for more comprehensive contrastive objective, a novel multi-channel pseudo-siamese network to further enable more expressive learning of mutual information within each scale. Comprehensive experimental results show HCL achieves competitive performance on 12 datasets involving node classification, node clustering and graph classification. In addition, the visualization of learned representation reveals that HCL successfully captures meaningful characteristics of graphs.

cs.LG↗
arXiv2022

Twists of graded Poisson algebras and related properties

We introduce a Poisson version of the graded twist of a graded associative algebra and prove that every graded Poisson structure on a connected graded polynomial ring $A:=\Bbbk[x_1,\ldots,x_n]$ is a graded twist of a unimodular Poisson structure on $A$, namely, if $π$ is a graded Poisson structure on $A$, then $π$ has a decomposition $$π=π_{unim} +\frac{1}{\sum_{i=1}^n {\rm deg} x_i} E\wedge {\mathbf m}$$ where $E$ is the Euler derivation, $π_{unim}$ is the unimodular graded Poisson structure on $A$ corresponding to $π$, and ${\mathbf m}$ is the modular derivation of $(A,π)$. This result is a generalization of the same result in the quadratic setting. The rigidity of graded twisting, $PH^1$-minimality, and $H$-ozoneness are studied. As an application, we compute the Poisson cohomologies of the quadratic Poisson structures on the polynomial ring of three variables when the potential is irreducible, but not necessarily having isolated singularities.

math.RA↗
arXiv2022

Auto-MLM: Improved Contrastive Learning for Self-supervised Multi-lingual Knowledge Retrieval

Contrastive learning (CL) has become a ubiquitous approach for several natural language processing (NLP) downstream tasks, especially for question answering (QA). However, the major challenge, how to efficiently train the knowledge retrieval model in an unsupervised manner, is still unresolved. Recently the commonly used methods are composed of CL and masked language model (MLM). Unexpectedly, MLM ignores the sentence-level training, and CL also neglects extraction of the internal info from the query. To optimize the CL hardly obtain internal information from the original query, we introduce a joint training method by combining CL and Auto-MLM for self-supervised multi-lingual knowledge retrieval. First, we acquire the fixed dimensional sentence vector. Then, mask some words among the original sentences with random strategy. Finally, we generate a new token representation for predicting the masked tokens. Experimental results show that our proposed approach consistently outperforms all the previous SOTA methods on both AliExpress $\&$ LAZADA service corpus and openly available corpora in 8 languages.

cs.CL↗
arXiv2021

End-to-end speaker diarization with transformer

Speaker diarization is connected to semantic segmentation in computer vision. Inspired from MaskFormer \cite{cheng2021per} which treats semantic segmentation as a set-prediction problem, we propose an end-to-end approach to predict a set of targets consisting of binary masks, vocal activities and speaker vectors. Our model, which we coin \textit{DiFormer}, is mainly based on a speaker encoder and a feature pyramid network (FPN) module to extract multi-scale speaker features which are then fed into a transformer encoder-decoder to predict a set of diarization targets from learned query embedding. To account for temporal characteristics of speech signal, bidirectional LSTMs are inserted into the mask prediction module to improve temporal consistency. Our model handles unknown number of speakers, speech overlaps, as well as vocal activity detection in a unified way. Experiments on multimedia and meeting datasets demonstrate the effectiveness of our approach.

cs.SD↗
arXiv2021

Visual-Semantic Transformer for Scene Text Recognition

Modeling semantic information is helpful for scene text recognition. In this work, we propose to model semantic and visual information jointly with a Visual-Semantic Transformer (VST). The VST first explicitly extracts primary semantic information from visual feature maps with a transformer module and a primary visual-semantic alignment module. The semantic information is then joined with the visual feature maps (viewed as a sequence) to form a pseudo multi-domain sequence combining visual and semantic information, which is subsequently fed into an transformer-based interaction module to enable learning of interactions between visual and semantic features. In this way, the visual features can be enhanced by the semantic information and vice versus. The enhanced version of visual features are further decoded by a secondary visual-semantic alignment module which shares weights with the primary one. Finally, the decoded visual features and the enhanced semantic features are jointly processed by the third transformer module obtaining the final text prediction. Experiments on seven public benchmarks including regular/ irregular text recognition datasets verifies the effectiveness our proposed model, reaching state of the art on four of the seven benchmarks.

cs.CV↗