arXiv subjects

Yang Xiao

Publications and source records attributed to Yang Xiao.

At least 163 records · Page 9Linked to original sources

arXiv2025

AdaKWS: Towards Robust Keyword Spotting with Test-Time Adaptation

Spoken keyword spotting (KWS) aims to identify keywords in audio for wide applications, especially on edge devices. Current small-footprint KWS systems focus on efficient model designs. However, their inference performance can decline in unseen environments or noisy backgrounds. Test-time adaptation (TTA) helps models adapt to test samples without needing the original training data. In this study, we present AdaKWS, the first TTA method for robust KWS to the best of our knowledge. Specifically, 1) We initially optimize the model's confidence by selecting reliable samples based on prediction entropy minimization and adjusting the normalization statistics in each batch. 2) We introduce pseudo-keyword consistency (PKC) to identify critical, reliable features without overfitting to noise. Our experiments show that AdaKWS outperforms other methods across various conditions, including Gaussian noise and real-scenario noises. The code will be released in due course.

eess.AS↗

arXiv2025

Listen, Analyze, and Adapt to Learn New Attacks: An Exemplar-Free Class Incremental Learning Method for Audio Deepfake Source Tracing

As deepfake speech becomes common and hard to detect, it is vital to trace its source. Recent work on audio deepfake source tracing (ST) aims to find the origins of synthetic or manipulated speech. However, ST models must adapt to learn new deepfake attacks while retaining knowledge of the previous ones. A major challenge is catastrophic forgetting, where models lose the ability to recognize previously learned attacks. Some continual learning methods help with deepfake detection, but multi-class tasks such as ST introduce additional challenges as the number of classes grows. To address this, we propose an analytic class incremental learning method called AnaST. When new attacks appear, the feature extractor remains fixed, and the classifier is updated with a closed-form analytical solution in one epoch. This approach ensures data privacy, optimizes memory usage, and is suitable for online training. The experiments carried out in this work show that our method outperforms the baselines.

eess.AS↗

arXiv2025

AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting

Keyword spotting (KWS) offers a vital mechanism to identify spoken commands in voice-enabled systems, where user demands often shift, requiring models to learn new keywords continually over time. However, a major problem is catastrophic forgetting, where models lose their ability to recognize earlier keywords. Although several continual learning methods have proven their usefulness for reducing forgetting, most existing approaches depend on storing and revisiting old data to combat catastrophic forgetting. Though effective, these methods face two practical challenges: 1) privacy risks from keeping user data and 2) large memory and time consumption that limit deployment on small devices. To address these issues, we propose an exemplar-free Analytic Continual Learning (AnalyticKWS) method that updates model parameters without revisiting earlier data. Inspired by efficient learning principles, AnalyticKWS computes a closed-form analytical solution for model updates and requires only a single epoch of adaptation for incoming keywords. AnalyticKWS demands fewer computational resources by avoiding gradient-based updates and does not store old data. By eliminating the need for back-propagation during incremental learning, the model remains lightweight and efficient. As a result, AnalyticKWS meets the challenges mentioned earlier and suits resource-limited settings well. Extensive experiments on various datasets and settings show that AnalyticKWS consistently outperforms existing continual learning methods.

eess.AS↗

arXiv2025

Quantum Lattice Kinetic Scheme for Solving Two-dimensional and Three-dimensional Incompressible Flows

Lattice Boltzmann method (LBM) is particularly well-suited for implementation on quantum circuits owing to its simple algebraic operations and natural parallelism. However, most quantum LBMs fix $τ$ = 1 to avoid nonlinear collision, which restricts the simulation to a fixed mesh size for a given Reynolds number. To preserve the simplicity of setting $τ$ = 1 while enhancing flexibility, we propose a quantum lattice kinetic scheme (LKS) by introducing a constant parameter $A$ into the equilibrium distribution function (EDF), enabling independent adjustment of the fluid's viscosity. This modification removes the constraint on mesh size, making it possible to simulate flows with arbitrary Reynolds numbers. The Chapman-Enskog analysis confirms the modified EDF still recovers the Navier-Stokes equations without compromising collision accuracy. We evaluate the method on 2D and 3D Taylor-Green vortex and lid-driven cavity flows, demonstrating that quantum LKS attains the same accuracy and convergence order as classical LKS. The first application of quantum LBM to 3D incompressible flows represents a significant step forward in large-scale fluid dynamics simulation.

quant-ph↗

arXiv2025

Correcting Noisy Multilabel Predictions: Modeling Label Noise through Latent Space Shifts

Noise in data appears to be inevitable in most real-world machine learning applications and would cause severe overfitting problems. Not only can data features contain noise, but labels are also prone to be noisy due to human input. In this paper, rather than noisy label learning in multiclass classifications, we instead focus on the less explored area of noisy label learning for multilabel classifications. Specifically, we investigate the post-correction of predictions generated from classifiers learned with noisy labels. The reasons are two-fold. Firstly, this approach can directly work with the trained models to save computational resources. Secondly, it could be applied on top of other noisy label correction techniques to achieve further improvements. To handle this problem, we appeal to deep generative approaches that are possible for uncertainty estimation. Our model posits that label noise arises from a stochastic shift in the latent variable, providing a more robust and beneficial means for noisy learning. We develop both unsupervised and semi-supervised learning methods for our model. The extensive empirical study presents solid evidence to that our approach is able to consistently improve the independent models and performs better than a number of existing methods across various noisy label settings. Moreover, a comprehensive empirical analysis of the proposed method is carried out to validate its robustness, including sensitivity analysis and an ablation study, among other elements.

cs.LG↗

arXiv2025

PhaseTracer2: from the effective potential to gravitational waves

In recent years, the prospect of detecting gravitational waves sourced from a strongly first-order cosmological phase transition has emerged as one of the most exciting frontiers of gravitational wave astronomy. Cosmological phase transitions are an essential ingredient in the Standard Model of particle cosmology, and help explain the mechanism for creation of matter in the early Universe, provide insights into fundamental theories of physics, and shed light on the nature of dark matter. This underscores the significance of developing robust end-to-end tools for determining the resulting gravitational waves from these phase transitions. In this article we present PhaseTracer2, an improved version of the C++ software package PhaseTracer, designed for mapping cosmological phases and transitions in Standard Model extensions of multiple scalar fields. Building on the robust framework of its predecessor, PhaseTracer2 extends its capabilities by including new features crucial for a more comprehensive analysis of cosmological phase transitions. It can calculate more complex properties, such as the bounce action through the path deformation method or an interface with BubbleProfiler, thermodynamic parameters, and gravitational wave spectra. Its applicability has also been broadened via incorporating the dimensionally reduced effective potential for models obtained from DRalgo, as well as calculations in the MSbar and OS-like renormalisation schemes. This modular, flexible, and practical upgrade retains the speed and stability of the original PhaseTracer, while significantly expanding its utility.

astro-ph.CO↗

arXiv2025

NGENT: Next-Generation AI Agents Must Integrate Multi-Domain Abilities to Achieve Artificial General Intelligence

This paper argues that the next generation of AI agent (NGENT) should integrate across-domain abilities to advance toward Artificial General Intelligence (AGI). Although current AI agents are effective in specialized tasks such as robotics, role-playing, and tool-using, they remain confined to narrow domains. We propose that future AI agents should synthesize the strengths of these specialized systems into a unified framework capable of operating across text, vision, robotics, reinforcement learning, emotional intelligence, and beyond. This integration is not only feasible but also essential for achieving the versatility and adaptability that characterize human intelligence. The convergence of technologies across AI domains, coupled with increasing user demand for cross-domain capabilities, suggests that such integration is within reach. Ultimately, the development of these versatile agents is a critical step toward realizing AGI. This paper explores the rationale for this shift, potential pathways for achieving it.

cs.AI↗

arXiv2025

Optimizing thermoelectric performance of graphene antidot lattices via quantum transport and machine-learning molecular dynamics simulations

Thermoelectric materials, which can convert waste heat to electricity or be utilized as solid-state coolers, hold promise for sustainable energy applications. However, optimizing thermoelectric performance remains a significant challenge due to the complex interplay between electronic and thermal transport properties. In this work, we systematically optimize $ZT$ in graphene antidot lattices (GALs), nanostructured graphene sheets with periodic nanopores characterized by two geometric parameters: the hexagonal unit cell side length $L$ and the antidot radius $R$. The lattice thermal conductivity is determined through machine-learned potential-driven molecular dynamics (MD) simulations, while electronic transport properties are computed using linear-scaling quantum transport in combination with MD trajectories based on a bond-length-dependent tight-binding model. This method is able to account for electron-phonon scattering, allowing access to diffusive transport in large-scale systems, overcoming limitations of previous methods based on nonequilibrium Green function formalism. Our results show that the introduction of the antidots effectively decouples lattice and electronic transport and lead to a favorable and significant violation of the Wiedemann-Franz law. We find that optimal $ZT$ values occur in GALs with intermediate $L$ and $R$, closely correlated with peak power factor values. Notably, thermoelectric performance peaks near room temperature, with maximal $ZT$ values approaching 2, highlighting GALs as promising candidates for high-performance thermoelectric energy conversion.

cond-mat.mes-hall↗

arXiv2025

RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization

3D reconstruction garners increasing attention alongside the advancement of high-level image applications, where dense stereo matching (DSM) serves as a pivotal technique. Previous studies often rely on publicly available datasets for training, focusing on modifying network architectures or incorporating specialized modules to extract domain-invariant features and thus improve model robustness. In contrast, inspired by single-frame structured-light phase-shifting encoding, this study introduces RGB-Speckle, a cross-scene 3D reconstruction framework based on an active stereo camera system, designed to enhance robustness. Specifically, we propose a novel phase pre-normalization encoding-decoding method: first, we randomly perturb phase-shift maps and embed them into the three RGB channels to generate color speckle patterns; subsequently, the camera captures phase-encoded images modulated by objects as input to a stereo matching network. This technique effectively mitigates external interference and ensures consistent input data for RGB-Speckle, thereby bolstering cross-domain 3D reconstruction stability. To validate the proposed method, we conduct complex experiments: (1) construct a color speckle dataset for complex scenarios based on the proposed encoding scheme; (2) evaluate the impact of the phase pre-normalization encoding-decoding technique on 3D reconstruction accuracy; and (3) further investigate its robustness across diverse conditions. Experimental results demonstrate that the proposed RGB-Speckle model offers significant advantages in cross-domain and cross-scene 3D reconstruction tasks, enhancing model generalization and reinforcing robustness in challenging environments, thus providing a novel solution for robust 3D reconstruction research.

eess.IV↗

arXiv2025

Leveraging Functional Encryption and Deep Learning for Privacy-Preserving Traffic Forecasting

Over the past few years, traffic congestion has continuously plagued the nation's transportation system creating several negative impacts including longer travel times, increased pollution rates, and higher collision risks. To overcome these challenges, Intelligent Transportation Systems (ITS) aim to improve mobility and vehicular systems, ensuring higher levels of safety by utilizing cutting-edge technologies, sophisticated sensing capabilities, and innovative algorithms. Drivers' participatory sensing, current/future location reporting, and machine learning algorithms have considerably improved real-time congestion monitoring and future traffic management. However, each driver's sensitive spatiotemporal location information can create serious privacy concerns. To address these challenges, we propose in this paper a secure, privacy-preserving location reporting and traffic forecasting system that guarantees privacy protection of driver data while maintaining high traffic forecasting accuracy. Our novel k-anonymity scheme utilizes functional encryption to aggregate encrypted location information submitted by drivers while ensuring the privacy of driver location data. Additionally, using the aggregated encrypted location information as input, this research proposes a deep learning model that incorporates a Convolutional-Long Short-Term Memory (Conv-LSTM) module to capture spatial and short-term temporal features and a Bidirectional Long Short-Term Memory (Bi-LSTM) module to recover long-term periodic patterns for traffic forecasting. With extensive evaluation on real datasets, we demonstrate the effectiveness of the proposed scheme with less than 10% mean absolute error for a 60-minute forecasting horizon, all while protecting driver privacy.

cs.CR↗

arXiv2025

A Novel Quantum Fourier Ordinary Differential Equation Solver for Solving Linear and Nonlinear Partial Differential Equations

In this work, a novel quantum Fourier ordinary differential equation (ODE) solver is proposed to solve both linear and nonlinear partial differential equations (PDEs). Traditional quantum ODE solvers transform a PDE into an ODE system via spatial discretization and then integrate it, thereby converting the task of solving the PDE into computing the integral for the driving function $f(x)$. These solvers rely on the quantum amplitude estimation algorithm, which requires the driving function $f(x)$ to be within the range of [0, 1] and necessitates the construction of a quantum circuit for the oracle R that encodes $f(x)$. This construction can be highly complex, even for simple functions like $f(x) = x$. An important exception arises for the specific case of $f(x) = sin^2(mx+c)$, which can be encoded more efficiently using a set of $Ry$ rotation gates. To address these challenges, we expand the driving function $f(x)$ as a Fourier series and propose the Quantum Fourier ODE Solver. This approach not only simplifies the construction of the oracle R but also removes the restriction that $f(x)$ must lie within [0,1]. The proposed method was evaluated by solving several representative linear and nonlinear PDEs, including the Navier-Stokes (N-S) equations. The results show that the quantum Fourier ODE solver produces results that closely match both analytical and reference solutions.

quant-ph↗

arXiv2025

Finite pattern problems related to Engel expansion

Let $\mathcal{F}$ be a countable collection of functions $f$ defined on the integers with integer values, such that for every $f\in \mathcal{F}$, $f(n)\to +\infty$ as $n\to +\infty$. This paper primarily investigates the Hausdorff dimension of the set of points whose digit sequences of the Engel expansion are strictly increasing and contain any finite pattern of $\mathcal{F}$, demonstrating applications with representative examples.

math.NT↗

arXiv2025

Two Heads Are Better than One: Model-Weight and Latent-Space Analysis for Federated Learning on Non-iid Data against Poisoning Attacks

Federated Learning is a popular paradigm that enables remote clients to jointly train a global model without sharing their raw data. However, FL has been shown to be vulnerable towards model poisoning attacks due to its distributed nature. Particularly, attackers acting as participants can upload arbitrary model updates that effectively compromise the global model of FL. While extensive research has been focusing on fighting against these attacks, we find that most of them assume data at remote clients are under iid while in practice they are inevitably non-iid. Our benchmark evaluations reveal that existing defenses generally fail to live up to their reputation when applied to various non-iid scenarios. In this paper, we propose a novel approach, GeminiGuard, that aims to address such a significant gap. We design GeminiGuard to be lightweight, versatile, and unsupervised so that it aligns well with the practical requirements of deploying such defenses. The key challenge from non-iids is that they make benign model updates look more similar to malicious ones. GeminiGuard is mainly built on two fundamental observations: (1) existing defenses based on either model-weight analysis or latent-space analysis face limitations in covering different MPAs and non-iid scenarios, and (2) model-weight and latent-space analysis are sufficiently different yet potentially complementary methods as MPA defenses. We hence incorporate a novel model-weight analysis component as well as a custom latent-space analysis component in GeminiGuard, aiming to further enhance its defense performance. We conduct extensive experiments to evaluate our defense across various settings, demonstrating its effectiveness in countering multiple types of untargeted and targeted MPAs, including adaptive ones. Our comprehensive evaluations show that GeminiGuard consistently outperforms SOTA defenses under various settings.

cs.LG↗

arXiv2025

Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering

Federated Learning (FL) is a popular paradigm enabling clients to jointly train a global model without sharing raw data. However, FL is known to be vulnerable towards backdoor attacks due to its distributed nature. As participants, attackers can upload model updates that effectively compromise FL. What's worse, existing defenses are mostly designed under independent-and-identically-distributed (iid) settings, hence neglecting the fundamental non-iid characteristic of FL. Here we propose FLBuff for tackling backdoor attacks even under non-iids. The main challenge for such defenses is that non-iids bring benign and malicious updates closer, hence harder to separate. FLBuff is inspired by our insight that non-iids can be modeled as omni-directional expansion in representation space while backdoor attacks as uni-directional. This leads to the key design of FLBuff, i.e., a supervised-contrastive-learning model extracting penultimate-layer representations to create a large in-between buffer layer. Comprehensive evaluations demonstrate that FLBuff consistently outperforms state-of-the-art defenses.

cs.CR↗

arXiv2025

Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning

As large language models (LLMs) continue to advance, ensuring their alignment with human values becomes increasingly critical. Traditional alignment methods heavily rely on human feedback to fine-tune models. With the emergence of superhuman models whose outputs may surpass human understanding, evaluating and aligning these models using human judgments poses significant challenges. To address the challenges, recent works use weak supervisors to elicit knowledge from much stronger models. However, there are important disanalogies between the empirical setup in the existing works and the genuine goal of alignment. We remark that existing works investigate the phenomenon of weak-to-strong generation in analogous setup (i.e., binary classification), rather than practical alignment-relevant tasks (e.g., safety). In this paper, we bridge this gap by extending weak-to-strong generation to the context of practical alignment. We empirically demonstrate the widespread phenomenon of weak-to-strong generation in three complicated alignment tasks: safety, toxicity, and legal reasoning}. Furthermore, we explore efficient strategies for improving alignment performance to enhance the quality of model outcomes. Lastly, we summarize and analyze the challenges and potential solutions in regard to specific alignment tasks, which we hope to catalyze the research progress on the topic of weak-to-strong generalization. Our code is released at https://github.com/yeruimeng/WTS.git.

cs.CL↗

arXiv2025

Where's That Voice Coming? Continual Learning for Sound Source Localization

Sound source localization (SSL) is essential for many speech-processing applications. Deep learning models have achieved high performance, but often fail when the training and inference environments differ. Adapting SSL models to dynamic acoustic conditions faces a major challenge: catastrophic forgetting. In this work, we propose an exemplar-free continual learning strategy for SSL (CL-SSL) to address such a forgetting phenomenon. CL-SSL applies task-specific sub-networks to adapt across diverse acoustic environments while retaining previously learned knowledge. It also uses a scaling mechanism to limit parameter growth, ensuring consistent performance across incremental tasks. We evaluated CL-SSL on simulated data with varying microphone distances and real-world data with different noise levels. The results demonstrate CL-SSL's ability to maintain high accuracy with minimal parameter increase, offering an efficient solution for SSL applications.

eess.AS↗

arXiv2025

OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI

The evolution of Artificial Intelligence (AI) has been significantly accelerated by advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), gradually showcasing potential cognitive reasoning abilities in problem-solving and scientific discovery (i.e., AI4Science) once exclusive to human intellect. To comprehensively evaluate current models' performance in cognitive reasoning abilities, we introduce OlympicArena, which includes 11,163 bilingual problems across both text-only and interleaved text-image modalities. These challenges encompass a wide range of disciplines spanning seven fields and 62 international Olympic competitions, rigorously examined for data leakage. We argue that the challenges in Olympic competition problems are ideal for evaluating AI's cognitive reasoning due to their complexity and interdisciplinary nature, which are essential for tackling complex scientific challenges and facilitating discoveries. Beyond evaluating performance across various disciplines using answer-only criteria, we conduct detailed experiments and analyses from multiple perspectives. We delve into the models' cognitive reasoning abilities, their performance across different modalities, and their outcomes in process-level evaluations, which are vital for tasks requiring complex reasoning with lengthy solutions. Our extensive evaluations reveal that even advanced models like GPT-4o only achieve a 39.97% overall accuracy, illustrating current AI limitations in complex reasoning and multimodal integration. Through the OlympicArena, we aim to advance AI towards superintelligence, equipping it to address more complex challenges in science and beyond. We also provide a comprehensive set of resources to support AI research, including a benchmark dataset, an open-source annotation platform, a detailed evaluation tool, and a leaderboard with automatic submission features.

cs.CL↗

arXiv2025

XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection

Transformers and their variants have achieved great success in speech processing. However, their multi-head self-attention mechanism is computationally expensive. Therefore, one novel selective state space model, Mamba, has been proposed as an alternative. Building on its success in automatic speech recognition, we apply Mamba for spoofing attack detection. Mamba is well-suited for this task as it can capture the artifacts in spoofed speech signals by handling long-length sequences. However, Mamba's performance may suffer when it is trained with limited labeled data. To mitigate this, we propose combining a new structure of Mamba based on a dual-column architecture with self-supervised learning, using the pre-trained wav2vec 2.0 model. The experiments show that our proposed approach achieves competitive results and faster inference on the ASVspoof 2021 LA and DF datasets, and on the more challenging In-the-Wild dataset, it emerges as the strongest candidate for spoofing attack detection. The code has been publicly released in https://github.com/swagshaw/XLSR-Mamba.

eess.AS↗