arXiv subjects

Kai Li

Publications and source records attributed to Kai Li.

At least 181 records · Page 10Linked to original sources

arXiv2025

Sheep Facial Pain Assessment Under Weighted Graph Neural Networks

Accurately recognizing and assessing pain in sheep is key to discern animal health and mitigating harmful situations. However, such accuracy is limited by the ability to manage automatic monitoring of pain in those animals. Facial expression scoring is a widely used and useful method to evaluate pain in both humans and other living beings. Researchers also analyzed the facial expressions of sheep to assess their health state and concluded that facial landmark detection and pain level prediction are essential. For this purpose, we propose a novel weighted graph neural network (WGNN) model to link sheep's detected facial landmarks and define pain levels. Furthermore, we propose a new sheep facial landmarks dataset that adheres to the parameters of the Sheep Facial Expression Scale (SPFES). Currently, there is no comprehensive performance benchmark that specifically evaluates the use of graph neural networks (GNNs) on sheep facial landmark data to detect and measure pain levels. The YOLOv8n detector architecture achieves a mean average precision (mAP) of 59.30% with the sheep facial landmarks dataset, among seven other detection models. The WGNN framework has an accuracy of 92.71% for tracking multiple facial parts expressions with the YOLOv8n lightweight on-board device deployment-capable model.

cs.CV↗

arXiv2025

BERP: A Blind Estimator of Room Parameters for Single-Channel Noisy Speech Signals

Room acoustical parameters (RAPs), room geometrical parameters (RGPs) and instantaneous occupancy level are essential metrics for parameterizing the room acoustical characteristics (RACs) of a sound field around a listener's local environment, offering comprehensive indications for various applications. Current blind estimation methods either fail to cover a broad range of real-world acoustic environments in the context of real background noise or estimate only a few RAPs and RGPs from noisy single-channel speech signals. In addition, they are limited in their ability to estimate the instantaneous occupancy level. In this paper, we propose a new universal blind estimation framework called the blind estimator of room parameters (BERP) to estimate RAPs, RGPs and occupancy level via a unified methodology. It consists of two modules: a unified room feature encoder that combines attention mechanisms with convolutional layers to learn common features across room parameters, and multiple separate parametric predictors for continuous estimation of each parameter in parallel. The combination of attention and convolutions enables the model to capture acoustic features locally and globally from speech, yielding more robust and multitask generalizable common features. Separate predictors allow the model to independently optimize for each room parameter to reduce task learning conflict and improve per-task performance. This estimation framework enables universal and efficient estimation of room parameters while maintaining satisfactory performance. To evaluate the effectiveness of the proposed framework, we compile a task-specific dataset from several publicly available datasets, including synthetic and real reverberant recordings. The results reveal that BERP achieves state-of-the-art (SOTA) performance and excellent adaptability to real-world scenarios. The code and weights are available on GitHub.

eess.AS↗

arXiv2025

Photometric and Spectroscopic Studies of Two Early-Type Eclipsing Binaries

Using high-precision photometric data from TESS, medium resolution spectroscopic data from LAMOST, and long-term eclipse timings, we provide orbital parameters for two early-type detached eclipsing binary systems: TYC 3740-2072-1 and TYC 2888-780-1, and analyze the orbital period variations and evolutionary status of these two targets. TYC 3740-2072-1, with a spectral type of B1V, consists of a $6.914 M_\odot$ subgiant and a $6.233 M_\odot$ main-sequence component. It is expected to evolve into a semi-detached binary, potentially serving as a progenitor of a Type Ia supernova. TYC 2888-780-1 has a spectral type of A3 and consists of two main-sequence components with masses of $1.682 M_\odot$ and $1.673 M_\odot$, respectively. It is undergoing stable evolution. Through eclipse timing analysis, we find that both targets exhibit apsidal motion effects, with observed AM rates of $\dotω_{obs} = 0.0412~\text{deg}~\text{cycle}^{-1}$ and $\dotω_{obs} = 0.0205~\text{deg}~\text{cycle}^{-1}$, respectively. Additionally, TYC 2888-780-1 exhibits orbital period variations, which we attribute to the light travel time effect caused by a third body, the minimum mass of this third body is estimated to be $0.598 M_\odot$.

astro-ph.SR↗

arXiv2025

Towards Automated Discovery of Asymmetric Mempool DoS in Blockchains

In blockchains, mempool controls transaction flow before consensus, denial of whose service hurts the health and security of blockchain networks. This paper presents MPFUZZ, the first mempool fuzzer to find asymmetric DoS bugs by exploring the space of symbolized mempool states and optimistically estimating the promisingness of an intermediate state in reaching bug oracles. Compared to the baseline blockchain fuzzers, MPFUZZ achieves a > 100x speedup in finding known DETER exploits. Running MPFUZZ on major Ethereum clients leads to discovering new mempool vulnerabilities, which exhibit a wide variety of sophisticated patterns, including stealthy mempool eviction and mempool locking. Rule-based mitigation schemes are proposed against all newly discovered vulnerabilities.

cs.CR↗

arXiv2025

Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things

This paper focuses on Zero-Trust Foundation Models (ZTFMs), a novel paradigm that embeds zero-trust security principles into the lifecycle of foundation models (FMs) for Internet of Things (IoT) systems. By integrating core tenets, such as continuous verification, least privilege access (LPA), data confidentiality, and behavioral analytics into the design, training, and deployment of FMs, ZTFMs can enable secure, privacy-preserving AI across distributed, heterogeneous, and potentially adversarial IoT environments. We present the first structured synthesis of ZTFMs, identifying their potential to transform conventional trust-based IoT architectures into resilient, self-defending ecosystems. Moreover, we propose a comprehensive technical framework, incorporating federated learning (FL), blockchain-based identity management, micro-segmentation, and trusted execution environments (TEEs) to support decentralized, verifiable intelligence at the network edge. In addition, we investigate emerging security threats unique to ZTFM-enabled systems and evaluate countermeasures, such as anomaly detection, adversarial training, and secure aggregation. Through this analysis, we highlight key open research challenges in terms of scalability, secure orchestration, interpretable threat attribution, and dynamic trust calibration. This survey lays a foundational roadmap for secure, intelligent, and trustworthy IoT infrastructures powered by FMs.

cs.CR↗

arXiv2025

ARS: Automatic Routing Solver with Large Language Models

Real-world Vehicle Routing Problems (VRPs) are characterized by a variety of practical constraints, making manual solver design both knowledge-intensive and time-consuming. Although there is increasing interest in automating the design of routing algorithms, existing research has explored only a limited array of VRP variants and fails to adequately address the complex and prevalent constraints encountered in real-world situations. To fill this gap, this paper introduces RoutBench, a benchmark of 1,000 VRP variants derived from 24 attributes, for evaluating the effectiveness of automatic routing solvers in addressing complex constraints. Along with RoutBench, we present the Automatic Routing Solver (ARS), which employs Large Language Model (LLM) agents to enhance a backbone algorithm framework by automatically generating constraint-aware heuristic code, based on problem descriptions and several representative constraints selected from a database. Our experiments show that ARS outperforms state-of-the-art LLM-based methods and commonly used solvers, automatically solving 91.67% of common VRPs and achieving at least a 30% improvement across all benchmarks.

cs.AI↗

arXiv2025

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously curated audio-question-answer triplets, collected from real-world internet videos and refined through iterative error corrections and quality checks to ensure high quality. Unlike existing benchmarks that are limited to specific domains of sound, music, or speech, MMAR extends them to a broad spectrum of real-world audio scenarios, including mixed-modality combinations of sound, music, and speech. Each question in MMAR is hierarchically categorized across four reasoning layers: Signal, Perception, Semantic, and Cultural, with additional sub-categories within each layer to reflect task diversity and complexity. To further foster research in this area, we annotate every question with a Chain-of-Thought (CoT) rationale to promote future advancements in audio reasoning. Each item in the benchmark demands multi-step deep reasoning beyond surface-level understanding. Moreover, a part of the questions requires graduate-level perceptual and domain-specific knowledge, elevating the benchmark's difficulty and depth. We evaluate MMAR using a broad set of models, including Large Audio-Language Models (LALMs), Large Audio Reasoning Models (LARMs), Omni Language Models (OLMs), Large Language Models (LLMs), and Large Reasoning Models (LRMs), with audio caption inputs. The performance of these models on MMAR highlights the benchmark's challenging nature, and our analysis further reveals critical limitations of understanding and reasoning capabilities among current models. We hope MMAR will serve as a catalyst for future advances in this important but little-explored area.

cs.SD↗

arXiv2025

Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation

Existing causal speech separation models often underperform compared to non-causal models due to difficulties in retaining historical information. To address this, we propose the Time-Frequency Attention Cache Memory (TFACM) model, which effectively captures spatio-temporal relationships through an attention mechanism and cache memory (CM) for historical information storage. In TFACM, an LSTM layer captures frequency-relative positions, while causal modeling is applied to the time dimension using local and global representations. The CM module stores past information, and the causal attention refinement (CAR) module further enhances time-based feature representations for finer granularity. Experimental results showed that TFACM achieveed comparable performance to the SOTA TF-GridNet-Causal model, with significantly lower complexity and fewer trainable parameters. For more details, visit the project page: https://cslikai.cn/TFACM/.

cs.SD↗

arXiv2025

DIMM: Decoupled Multi-hierarchy Kalman Filter for 3D Object Tracking

State estimation is challenging for 3D object tracking with high maneuverability, as the target's state transition function changes rapidly, irregularly, and is unknown to the estimator. Existing work based on interacting multiple model (IMM) achieves more accurate estimation than single-filter approaches through model combination, aligning appropriate models for different motion modes of the target object over time. However, two limitations of conventional IMM remain unsolved. First, the solution space of the model combination is constrained as the target's diverse kinematic properties in different directions are ignored. Second, the model combination weights calculated by the observation likelihood are not accurate enough due to the measurement uncertainty. In this paper, we propose a novel framework, DIMM, to effectively combine estimates from different motion models in each direction, thus increasing the 3D object tracking accuracy. First, DIMM extends the model combination solution space of conventional IMM from a hyperplane to a hypercube by designing a 3D-decoupled multi-hierarchy filter bank, which describes the target's motion with various-order linear models. Second, DIMM generates more reliable combination weight matrices through a differentiable adaptive fusion network for importance allocation rather than solely relying on the observation likelihood; it contains an attention-based twin delayed deep deterministic policy gradient (TD3) method with a hierarchical reward. Experiments demonstrate that DIMM significantly improves the tracking accuracy of existing state estimation methods by 31.61%~99.23%.

cs.CV↗

arXiv2025

SepPrune: Structured Pruning for Efficient Deep Speech Separation

Although deep learning has substantially advanced speech separation in recent years, most existing studies continue to prioritize separation quality while overlooking computational efficiency, an essential factor for low-latency speech processing in real-time applications. In this paper, we propose SepPrune, the first structured pruning framework specifically designed to compress deep speech separation models and reduce their computational cost. SepPrune begins by analyzing the computational structure of a given model to identify layers with the highest computational burden. It then introduces a differentiable masking strategy to enable gradient-driven channel selection. Based on the learned masks, SepPrune prunes redundant channels and fine-tunes the remaining parameters to recover performance. Extensive experiments demonstrate that this learnable pruning paradigm yields substantial advantages for channel pruning in speech separation models, outperforming existing methods. Notably, a model pruned with SepPrune can recover 85% of the performance of a pre-trained model (trained over hundreds of epochs) with only one epoch of fine-tuning, and achieves convergence 36$\times$ faster than training from scratch. Code is available at https://github.com/itsnotacie/SepPrune.

cs.SD↗

arXiv2025

Extremely Low Mass Ratio Contact Binaries. II. The First Photometric and Spectroscopic Investigations of Six Systems with Orbital Periods Longer than 0.5 days

The photometric and spectroscopic studies of six contact binaries were performed for the first time. The orbital periods of all the six targets are longer than 0.5d, and we discovered that their mass ratios are smaller than 0.15. So, they are extremely low mass-ratio contact binaries. Only one target is a W-subtype contact binary (ASASSN-V J105032.88+420829.0), while the others are A-subtype contact binaries. From orbital period analysis, ASASSN-V J075442.44+555623.2 shows no orbital period change. Three of the six targets demonstrate a secular period increase, and two targets for a secular period decrease. We investigated the LAMOST spectra employing the spectral subtraction method. All six contact binaries show no chromospheric emission line, implying no chromospheric activity. Their absolute parameters, initial masses, ages, energy transfer parameters, and instability parameters were calculated. The bolometric luminosity ratios ($(L_2/L_1)_{bol}$), the energy transfer parameters ($β$), the contact degrees ($f$), and the mass ratios ($q$) were collected for a sample of 218 contact binaries and we analyzed and discussed some correlations. The results by analyzing the relation between $β$, $f$ and $q$ indicate that the energy transfer parameter between the two components of extremely low mass-ratio contact binaries is independent of the contact degree. And the predicted cutoff mass ratio was estimated as 0.021 by analyzing the relation between $f$ and $q$.

astro-ph.SR↗

arXiv2025

Bremsstrahlung radiation power in non-Maxwellian plasmas

In plasmas, bremsstrahlung includes electron-ion (e-i) bremsstrahlung and electron-electron (e-e) bremsstrahlung. Bremsstrahlung radiation power loss is one of the most significant losses in fusion plasmas, which is more pronounced in higher temperature fusion. The factors that affect bremsstrahlung power include the mean electron energy and the electron velocity distribution shape. In this study, we systematically study the influence of the electron velocity distribution shape on the bremsstrahlung power with fixed total electron energy. It was found that the existing electron velocity distribution shapes have little effect on the bremsstrahlung power. In addition, by analyzing the bounds of bremsstrahlung power, we have provided the theoretical upper and lower bounds of e-i radiation. Our analysis reveals that the e-i bremsstrahlung power depends critically on the degree of energy distribution concentration. Specifically, in non-relativistic regimes, concentrated energy distributions enhance the radiation power, whereas in high-temperature relativistic regimes, such concentration suppresses it. This discrepancy arises from the distinct contributions of high-energy electron populations to radiation power across different energy regimes. For e-e bremsstrahlung, a similar dependence on energy concentration is observed. Furthermore, e-e radiation power exhibits additional sensitivity to the anisotropy of the electron velocity distribution function. These rules could provide a basis for reducing bremsstrahlung power losses in fusion plasmas.

physics.plasm-ph↗

arXiv2025

PolyFootNet: Extracting Polygonal Building Footprints in Off-Nadir Remote Sensing Images

Extracting polygonal building footprints from off-nadir imagery is crucial for diverse applications. Current deep-learning-based extraction approaches predominantly rely on semantic segmentation paradigms and post-processing algorithms, limiting their boundary precision and applicability. However, existing polygonal extraction methodologies are inherently designed for near-nadir imagery and fail under the geometric complexities introduced by off-nadir viewing angles. To address these challenges, this paper introduces Polygonal Footprint Network (PolyFootNet), a novel deep-learning framework that directly outputs polygonal building footprints without requiring external post-processing steps. PolyFootNet employs a High-Quality Mask Prompter to generate precise roof masks, which guide polygonal vertex extraction in a unified model pipeline. A key contribution of PolyFootNet is introducing the Self Offset Attention mechanism, grounded in Nadaraya-Watson regression, to effectively mitigate the accuracy discrepancy observed between low-rise and high-rise buildings. This approach allows low-rise building predictions to leverage angular corrections learned from high-rise building offsets, significantly enhancing overall extraction accuracy. Additionally, motivated by the inherent ambiguity of building footprint extraction tasks, we systematically investigate alternative extraction paradigms and demonstrate that a combined approach of building masks and offsets achieves superior polygonal footprint results. Extensive experiments validate PolyFootNet's effectiveness, illustrating its promising potential as a robust, generalizable, and precise polygonal building footprint extraction method from challenging off-nadir imagery. To facilitate further research, we will release pre-trained weights of our offset prediction module at https://github.com/likaiucas/PolyFootNet.

cs.CV↗

arXiv2025

Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network

Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data. To address these challenges, we first introduce a cooperative unfolding network that jointly models atmospheric scattering and image scenes, effectively integrating physical knowledge into deep networks to restore haze-contaminated details. Additionally, we propose the first RID-oriented iterative mean-teacher framework, termed the Coherence-based Label Generator, to generate high-quality pseudo labels for network training. Specifically, we provide an optimal label pool to store the best pseudo-labels during network training, leveraging both global and local coherence to select high-quality candidates and assign weights to prioritize haze-free regions. We verify the effectiveness of our method, with experiments demonstrating that it achieves state-of-the-art performance on RID tasks. Code will be available at https://github.com/cnyvfang/CORUN-Colabator.

cs.CV↗

arXiv2025

Undermining Federated Learning Accuracy in EdgeIoT via Variational Graph Auto-Encoders

EdgeIoT represents an approach that brings together mobile edge computing with Internet of Things (IoT) devices, allowing for data processing close to the data source. Sending source data to a server is bandwidth-intensive and may compromise privacy. Instead, federated learning allows each device to upload a shared machine-learning model update with locally processed data. However, this technique, which depends on aggregating model updates from various IoT devices, is vulnerable to attacks from malicious entities that may inject harmful data into the learning process. This paper introduces a new attack method targeting federated learning in EdgeIoT, known as data-independent model manipulation attack. This attack does not rely on training data from the IoT devices but instead uses an adversarial variational graph auto-encoder (AV-GAE) to create malicious model updates by analyzing benign model updates intercepted during communication. AV-GAE identifies and exploits structural relationships between benign models and their training data features. By manipulating these structural correlations, the attack maximizes the training loss of the federated learning system, compromising its overall effectiveness.

cs.LG↗

arXiv2025

A 0.3\% calibration of the W UMa-type contact binary luminosity based on Gaia DR3

W Ursa Majoris (W UMa)-type contact binary systems (CBs) with period--luminosity (PL) relations are valuable distance indicators. The PL relations of CBs are affected by metallicity. Here, we establish PL relations and period--luminosity--metallicity (PLZ) relations in nine bands from optical to mid-infrared ($BP$, $G$, $RP$, $J$, $H$, $K_S$, $W1$, $W2$, $W3$) and in five Wesenheit bands based on Gaia DR3 parallaxes. The dispersion of PLZ relations gradually decreases from the optical to mid-infrared bands, with the minimum dispersion of 0.138 mag. We fit the best PL relations for three bands ($W1$, $W_{G,BP,RP}$, $W_{W1,BP,RP}$) under different parallax uncertainty criteria and determine a parallax (after correction) zero point of $zp_\varpi=24\pm4$ $μ$as. After fixing the parallax zero point, we find that the total zero errors of the PL and PLZ relation are smallest when the parallax uncertainty is less than 2\%, resulting in a calibrated CB luminosity with an accuracy of 0.33\%, which is more accurate than the classical Cepheids. Furthermore, by examining the absolute magnitude residuals in different metallicity intervals, we find that the use of a linear metallicity effect is appropriate for CBs with different metallicities. These results indicate that CBs are excellent standard candles.

astro-ph.SR↗

arXiv2025

Using machine learning method for variable star classification using the TESS Sectors 1-57 data

The Transiting Exoplanet Survey Satellite (TESS) is a wide-field all-sky survey mission designed to detect Earth-sized exoplanets. After over four years photometric surveys, data from sectors 1-57, including approximately 1,050,000 light curves with a 2-minute cadence, were collected. By cross-matching the data with Gaia's variable star catalogue, we obtained labeled datasets for further analysis. Using a random forest classifier, we performed classification of variable stars and designed distinct classification processes for each subclass, 6770 EA, 2971 EW, 980 CEP, 8347 DSCT, 457 RRab, 404 RRc and 12348 ROT were identified. Each variable star was visually inspected to ensure the reliability and accuracy of the compiled catalog. Subsequently, we ultimately obtained 6046 EA, 3859 EW, 2058 CEP, 8434 DSCT, 482 RRab, 416 RRc, and 9694 ROT, and a total of 14092 new variable stars were discovered.

astro-ph.SR↗

arXiv2025

Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends

In this survey, we investigate the most recent techniques of resilient federated learning (ResFL) in CyberEdge networks, focusing on joint training with agglomerative deduction and feature-oriented security mechanisms. We explore adaptive hierarchical learning strategies to tackle non-IID data challenges, improving scalability and reducing communication overhead. Fault tolerance techniques and agglomerative deduction mechanisms are studied to detect unreliable devices, refine model updates, and enhance convergence stability. Unlike existing FL security research, we comprehensively analyze feature-oriented threats, such as poisoning, inference, and reconstruction attacks that exploit model features. Moreover, we examine resilient aggregation techniques, anomaly detection, and cryptographic defenses, including differential privacy and secure multi-party computation, to strengthen FL security. In addition, we discuss the integration of 6G, large language models (LLMs), and interoperable learning frameworks to enhance privacy-preserving and decentralized cross-domain training. These advancements offer ultra-low latency, artificial intelligence (AI)-driven network management, and improved resilience against adversarial attacks, fostering the deployment of secure ResFL in CyberEdge networks.

cs.CR↗