arXiv subjects

Wenyu Wang

Publications and source records attributed to Wenyu Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Dark Photon Oscillations in Waveguide

Dark photons, which can kinetically mix with ordinary photons, represent the simplest extension to the standard model. Detecting their oscillations with visible photons could provide crucial insights into the nature of dark matter and fundamental interactions beyond the standard model. We propose a novel laboratory-based approach to detect dark photon oscillations using a laser in an Optical Time-domain Relectometry (OTDR) setup. The laser light propagating through the optical fiber undergoes oscillations with the dark photon, leading to measurable changes in the power flow. These oscillations can precisely measured, leveraging its high sensitivity and efficiency in detecting small variations in the optical signal. This approach could provide a new avenue for probing dark photon oscillations in the laboratory and greatly improve the current experimental sensitivity to dark photon in a wide mass range.

hep-ph↗

arXiv2025

Leveraging Geometric Visual Illusions as Perceptual Inductive Biases for Vision Models

Contemporary deep learning models have achieved impressive performance in image classification by primarily leveraging statistical regularities within large datasets, but they rarely incorporate structured insights drawn directly from perceptual psychology. To explore the potential of perceptually motivated inductive biases, we propose integrating classic geometric visual illusions well-studied phenomena from human perception into standard image-classification training pipelines. Specifically, we introduce a synthetic, parametric geometric-illusion dataset and evaluate three multi-source learning strategies that combine illusion recognition tasks with ImageNet classification objectives. Our experiments reveal two key conceptual insights: (i) incorporating geometric illusions as auxiliary supervision systematically improves generalization, especially in visually challenging cases involving intricate contours and fine textures; and (ii) perceptually driven inductive biases, even when derived from synthetic stimuli traditionally considered unrelated to natural image recognition, can enhance the structural sensitivity of both CNN and transformer-based architectures. These results demonstrate a novel integration of perceptual science and machine learning and suggest new directions for embedding perceptual priors into vision model design.

cs.CV↗

arXiv2025

Generative Modeling for Adversarial Lane-Change Scenarios

Decision-making in long-tail scenarios is pivotal to autonomous-driving development, and realistic and challenging simulations play a crucial role in testing safety-critical situations. However, existing open-source datasets lack systematic coverage of long-tail scenes, and lane-change maneuvers being emblematic, rendering such data exceedingly scarce. To bridge this gap, we introduce a data mining framework that exhaustively analyzes two widely used datasets, NGSIM and INTERACTION, to identify sequences marked by hazardous behavior, thereby replenishing these neglected scenarios. Using Generative Adversarial Imitation Learning (GAIL) enhanced with Proximal Policy Optimization (PPO), and enriched by vehicular-environment interaction analytics, our method iteratively refines and parameterizes newly generated trajectories. Distinguished by a rationally adversarial and sensitivity-aware perspective, the approach optimizes the creation of challenging scenes. Experiments show that, compared to unfiltered data and baseline models, our method produces behaviors that are simultaneously both adversarial and natural, judged by collision frequency, acceleration profiles, and lane-change dynamics, offering constructive insights to amplifying long-tailed lane-change instances in datasets and advancing decision-making training.

cs.RO↗

arXiv2025

HRS: Hybrid Representation Framework with Scheduling Awareness for Time Series Forecasting in Crowdsourced Cloud-Edge Platforms

With the rapid proliferation of streaming services, network load exhibits highly time-varying and bursty behavior, posing serious challenges for maintaining Quality of Service (QoS) in Crowdsourced Cloud-Edge Platforms (CCPs). While CCPs leverage Predict-then-Schedule architecture to improve QoS and profitability, accurate load forecasting remains challenging under traffic surges. Existing methods either minimize mean absolute error, resulting in underprovisioning and potential Service Level Agreement (SLA) violations during peak periods, or adopt conservative overprovisioning strategies, which mitigate SLA risks at the expense of increased resource expenditure. To address this dilemma, we propose HRS, a hybrid representation framework with scheduling awareness that integrates numerical and image-based representations to better capture extreme load dynamics. We further introduce a Scheduling-Aware Loss (SAL) that captures the asymmetric impact of prediction errors, guiding predictions that better support scheduling decisions. Extensive experiments on four real-world datasets demonstrate that HRS consistently outperforms ten baselines and achieves state-of-the-art performance, reducing SLA violation rates by 63.1% and total profit loss by 32.3%.

cs.LG↗

arXiv2025

DFed-SST: Building Semantic- and Structure-aware Topologies for Decentralized Federated Graph Learning

Decentralized Federated Learning (DFL) has emerged as a robust distributed paradigm that circumvents the single-point-of-failure and communication bottleneck risks of centralized architectures. However, a significant challenge arises as existing DFL optimization strategies, primarily designed for tasks such as computer vision, fail to address the unique topological information inherent in the local subgraph. Notably, while Federated Graph Learning (FGL) is tailored for graph data, it is predominantly implemented in a centralized server-client model, failing to leverage the benefits of decentralization.To bridge this gap, we propose DFed-SST, a decentralized federated graph learning framework with adaptive communication. The core of our method is a dual-topology adaptive communication mechanism that leverages the unique topological features of each client's local subgraph to dynamically construct and optimize the inter-client communication topology. This allows our framework to guide model aggregation efficiently in the face of heterogeneity. Extensive experiments on eight real-world datasets consistently demonstrate the superiority of DFed-SST, achieving 3.26% improvement in average accuracy over baseline methods.

cs.LG↗

arXiv2025

A Trajectory-Based Bayesian Approach to Multi-Objective Hyperparameter Optimization with Epoch-Aware Trade-Offs

Training machine learning models inherently involves a resource-intensive and noisy iterative learning procedure that allows epoch-wise monitoring of the model performance. However, the insights gained from the iterative learning procedure typically remain underutilized in multi-objective hyperparameter optimization scenarios. Despite the limited research in this area, existing methods commonly identify the trade-offs only at the end of model training, overlooking the fact that trade-offs can emerge at earlier epochs in cases such as overfitting. To bridge this gap, we propose an enhanced multi-objective hyperparameter optimization problem that treats the number of training epochs as a decision variable, rather than merely an auxiliary parameter, to account for trade-offs at an earlier training stage. To solve this problem and accommodate its iterative learning, we then present a trajectory-based multi-objective Bayesian optimization algorithm characterized by two features: 1) a novel acquisition function that captures the improvement along the predictive trajectory of model performances over epochs for any hyperparameter setting and 2) a multi-objective early stopping mechanism that determines when to terminate the training to maximize epoch efficiency. Experiments on synthetic simulations and hyperparameter tuning benchmarks demonstrate that our algorithm can effectively identify the desirable trade-offs while improving tuning efficiency.

cs.LG↗

arXiv2025

AVENet: Disentangling Features by Approximating Average Features for Voice Conversion

Voice conversion (VC) has made progress in feature disentanglement, but it is still difficult to balance timbre and content information. This paper evaluates the pre-trained model features commonly used in voice conversion, and proposes an innovative method for disentangling speech feature representations. Specifically, we first propose an ideal content feature, referred to as the average feature, which is calculated by averaging the features within frame-level aligned parallel speech (FAPS) data. For generating FAPS data, we utilize a technique that involves freezing the duration predictor in a Text-to-Speech system and manipulating speaker embedding. To fit the average feature on traditional VC datasets, we then design the AVENet to take features as input and generate closely matching average features. Experiments are conducted on the performance of AVENet-extracted features within a VC system. The experimental results demonstrate its superiority over multiple current speech feature disentangling methods. These findings affirm the effectiveness of our disentanglement approach.

cs.SD↗

arXiv2025

M$^2$CD: A Unified MultiModal Framework for Optical-SAR Change Detection with Mixture of Experts and Self-Distillation

Most existing change detection (CD) methods focus on optical images captured at different times, and deep learning (DL) has achieved remarkable success in this domain. However, in extreme scenarios such as disaster response, synthetic aperture radar (SAR), with its active imaging capability, is more suitable for providing post-event data. This introduces new challenges for CD methods, as existing weight-sharing Siamese networks struggle to effectively learn the cross-modal data distribution between optical and SAR images. To address this challenge, we propose a unified MultiModal CD framework, M$^2$CD. We integrate Mixture of Experts (MoE) modules into the backbone to explicitly handle diverse modalities, thereby enhancing the model's ability to learn multimodal data distributions. Additionally, we innovatively propose an Optical-to-SAR guided path (O2SP) and implement self-distillation during training to reduce the feature space discrepancy between different modalities, further alleviating the model's learning burden. We design multiple variants of M$^2$CD based on both CNN and Transformer backbones. Extensive experiments validate the effectiveness of the proposed framework, with the MiT-b1 version of M$^2$CD outperforming all state-of-the-art (SOTA) methods in optical-SAR CD tasks.

cs.CV↗

arXiv2025

Wearable intelligent throat enables natural speech in stroke patients with dysarthria

Wearable silent speech systems hold significant potential for restoring communication in patients with speech impairments. However, seamless, coherent speech remains elusive, and clinical efficacy is still unproven. Here, we present an AI-driven intelligent throat (IT) system that integrates throat muscle vibrations and carotid pulse signal sensors with large language model (LLM) processing to enable fluent, emotionally expressive communication. The system utilizes ultrasensitive textile strain sensors to capture high-quality signals from the neck area and supports token-level processing for real-time, continuous speech decoding, enabling seamless, delay-free communication. In tests with five stroke patients with dysarthria, IT's LLM agents intelligently corrected token errors and enriched sentence-level emotional and logical coherence, achieving low error rates (4.2% word error rate, 2.9% sentence error rate) and a 55% increase in user satisfaction. This work establishes a portable, intuitive communication platform for patients with dysarthria with the potential to be applied broadly across different neurological conditions and in multi-language support systems.

eess.AS↗

arXiv2025

UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets

Large Language Models (LLMs) inevitably acquire harmful information during training on massive datasets. LLM unlearning aims to eliminate the influence of such harmful information while maintaining the model's overall performance. Existing unlearning methods, represented by gradient ascent-based approaches, primarily focus on forgetting target data while overlooking the crucial impact of logically related knowledge on the effectiveness of unlearning. In this paper, through both theoretical and experimental analyses, we first demonstrate that a key reason for the suboptimal unlearning performance is that models can reconstruct the target content through reasoning with logically related knowledge. To address this issue, we propose Unlearning Improvement via Parameter Extrapolation (UIPE), a method that removes knowledge highly correlated with the forgetting targets. Experimental results show that UIPE significantly enhances the performance of various mainstream LLM unlearning methods on the TOFU benchmark.

cs.CL↗

arXiv2025

SYKI-SVC: Advancing Singing Voice Conversion with Post-Processing Innovations and an Open-Source Professional Testset

Singing voice conversion aims to transform a source singing voice into that of a target singer while preserving the original lyrics, melody, and various vocal techniques. In this paper, we propose a high-fidelity singing voice conversion system. Our system builds upon the SVCC T02 framework and consists of three key components: a feature extractor, a voice converter, and a post-processor. The feature extractor utilizes the ContentVec and Whisper models to derive F0 contours and extract speaker-independent linguistic features from the input singing voice. The voice converter then integrates the extracted timbre, F0, and linguistic content to synthesize the target speaker's waveform. The post-processor augments high-frequency information directly from the source through simple and effective signal processing to enhance audio quality. Due to the lack of a standardized professional dataset for evaluating expressive singing conversion systems, we have created and made publicly available a specialized test set. Comparative evaluations demonstrate that our system achieves a remarkably high level of naturalness, and further analysis confirms the efficacy of our proposed system design.

cs.SD↗

arXiv2024

Probing levitodynamics with multi-stochastic forces and the simple applications on the dark matter detection in optical levitation experiment

If the terrestrial environment is permeated by dark matter, the levitation experiences damping forces and fluctuations attributed to dark matter. This paper investigates levitodynamics with multiple stochastic forces, including thermal drag, photon recoil, feedback, etc., assuming that all of these forces adhere to the fluctuation-dissipation theorem. The ratio of total damping to the stochastic damping coefficient distinguishes the levitodynamics from cases involving only one single stochastic force. The heating and cooling processes are formulated to determine the limits of temperature change. All sources of stochastic forces are comprehensively examined, revealing that dark matter collisions cannot be treated analogously to fluid dynamics. Additionally, a meticulous analysis is presented, elucidating the intricate relationship between the fundamental transfer cross-section and the macroscopic transfer cross-section. While the dark damping coefficient is suppressed by the mass of the levitated particle, scattering can be coherently enhanced based on the scale of the component microscopic particle, the atomic form factor, and the static structure factor. Hence, dark damping holds the potential to provide valuable insights into the detection of the macroscopic strength of fundamental particles. We propose experimental procedures for levitation and employ linear estimation to extract the dark damping coefficient. Utilizing current levitation results, we demonstrate that the fundamental transfer cross section of dark matter can be of the order $σ^{\rm D}_{T}\lsim {\cal O}(10^{-26})\rm cm^2$.

cond-mat.stat-mech↗

arXiv2024

FGCL: Fine-grained Contrastive Learning For Mandarin Stuttering Event Detection

This paper presents the T031 team's approach to the StutteringSpeech Challenge in SLT2024. Mandarin Stuttering Event Detection (MSED) aims to detect instances of stuttering events in Mandarin speech. We propose a detailed acoustic analysis method to improve the accuracy of stutter detection by capturing subtle nuances that previous Stuttering Event Detection (SED) techniques have overlooked. To this end, we introduce the Fine-Grained Contrastive Learning (FGCL) framework for MSED. Specifically, we model the frame-level probabilities of stuttering events and introduce a mining algorithm to identify both easy and confusing frames. Then, we propose a stutter contrast loss to enhance the distinction between stuttered and fluent speech frames, thereby improving the discriminative capability of stuttered feature embeddings. Extensive evaluations on English and Mandarin datasets demonstrate the effectiveness of FGCL, achieving a significant increase of over 5.0% in F1 score on Mandarin data.

cs.SD↗

arXiv2024

Adaptive Blind Beamforming for Intelligent Surface

Configuring intelligent surface (IS) or passive antenna array without any channel knowledge, namely blind beamforming, is a frontier research topic in the wireless communication field. Existing methods in the previous literature for blind beamforming include the RFocus and the CSM, the effectiveness of which has been demonstrated on hardware prototypes. However, this paper points out a subtle issue with these blind beamforming algorithms: the RFocus and the CSM may fail to work in the non-line-of-sight (NLoS) channel case. To address this issue, we suggest a grouping strategy that enables adaptive blind beamforming. Specifically, the reflective elements (REs) of the IS are divided into three groups; each group is configured randomly to obtain a dataset of random samples. We then extract the statistical feature of the wireless environment from the random samples, thereby coordinating phase shifts of the IS without channel acquisition. The RE grouping plays a critical role in guaranteeing performance gain in the NLoS case. In particular, if we place all the REs in the same group, the proposed algorithm would reduce to the RFocus and the CSM. We validate the advantage of the proposed blind beamforming algorithm in the real-world networks at 3.5 GHz aside from simulations.

cs.IT↗

arXiv2024

Power Allocation for Finite-Blocklength IR-HARQ

This letter concerns the power allocation across the multiple transmission rounds under the Incremental Redundancy Hybrid Automatic Repeat reQuest (IR-HARQ) policy, in pursuit of an energy-efficient way of fulfilling the outage probability target in the finite-blocklength regime. We start by showing that the optimization objective and the constraints of the above power allocation problem all depend upon the outage probability. The main challenge then lies in the fact that the outage probability cannot be written analytically in terms of the power variables. To sidestep this difficulty, we propose a novel upper bound on the outage probability in the finite-blocklength regime, which is much tighter than the existing ones from the literature. Most importantly, by using this upper bound to approximate the outage probability, we can recast the original intractable power allocation problem into a geometric programming (GP) form--which can be efficiently solved by the standard method.

cs.IT↗

arXiv2024

Medical Image Segmentation via Single-Source Domain Generalization with Random Amplitude Spectrum Synthesis

The field of medical image segmentation is challenged by domain generalization (DG) due to domain shifts in clinical datasets. The DG challenge is exacerbated by the scarcity of medical data and privacy concerns. Traditional single-source domain generalization (SSDG) methods primarily rely on stacking data augmentation techniques to minimize domain discrepancies. In this paper, we propose Random Amplitude Spectrum Synthesis (RASS) as a training augmentation for medical images. RASS enhances model generalization by simulating distribution changes from a frequency perspective. This strategy introduces variability by applying amplitude-dependent perturbations to ensure broad coverage of potential domain variations. Furthermore, we propose random mask shuffle and reconstruction components, which can enhance the ability of the backbone to process structural information and increase resilience intra- and cross-domain changes. The proposed Random Amplitude Spectrum Synthesis for Single-Source Domain Generalization (RAS^4DG) is validated on 3D fetal brain images and 2D fundus photography, and achieves an improved DG segmentation performance compared to other SSDG models.

cs.CV↗

arXiv2024

Ignorance Is Bliss: The Screening Effect of (Noisy) Information

This paper studies the value of a firm's internal information when the firm faces an adverse selection problem arising from unobservable managerial abilities. While more precise information allows the firm to make ex post more efficient investment decisions, noisier information has an ex ante screening effect that allows the firm to attract on-average better managers. The trade-off between more effective screening of managers and more informed investment implies a non-monotonic relationship between firm value and information quality. A marginal improvement in information quality does not necessarily lead to an overall improvement in firm value.

econ.TH↗

arXiv2024

Cross-Lingual Word Alignment for ASEAN Languages with Contrastive Learning

Cross-lingual word alignment plays a crucial role in various natural language processing tasks, particularly for low-resource languages. Recent study proposes a BiLSTM-based encoder-decoder model that outperforms pre-trained language models in low-resource settings. However, their model only considers the similarity of word embedding spaces and does not explicitly model the differences between word embeddings. To address this limitation, we propose incorporating contrastive learning into the BiLSTM-based encoder-decoder framework. Our approach introduces a multi-view negative sampling strategy to learn the differences between word pairs in the shared cross-lingual embedding space. We evaluate our model on five bilingual aligned datasets spanning four ASEAN languages: Lao, Vietnamese, Thai, and Indonesian. Experimental results demonstrate that integrating contrastive learning consistently improves word alignment accuracy across all datasets, confirming the effectiveness of the proposed method in low-resource scenarios. We will release our data set and code to support future research on ASEAN or more low-resource word alignment.

cs.CL↗