arXiv subjects

Biao Chen

Publications and source records attributed to Biao Chen.

At least 19 recordsLinked to original sources

arXiv2026

U-shaped Multi-granularity Learning for Vision-Language Models

The prompt learning paradigm for vision-language models is effective yet faces a granularity dilemma: global prompts lack fine-grained semantic awareness, while local prompts ignore contextual associations, limiting cross-task generalization. This dilemma exists in dense prediction tasks. Inspired by U-Net, which unifies multi-level representations across granularities, we propose UPrompt, a U-shaped multi-granularity prompt learning framework for vision-language models. Similar to how U-Net integrates fine and coarse features through symmetric encoder-decoder pathways with cross-level connections, UPrompt constructs parallel multi-granularity representations in both visual and textual modalities, where coarse-to-fine cascaded enhancement propagates global context to refine local details, while fine-to-coarse hierarchical supervision ensures semantic consistency across scales. Extensive experiments on 17 benchmarks validate our effectiveness. UPrompt outperforms MAMET and VPKE by 4.1 and 7.3 rSum on MSCOCO, surpasses CoCoA-Mix by 5.09% in base-to-novel generalization, while maintaining competitive performance with minimal overhead (coarse-grained) and matching PSRC with 1/3 cost (medium-grained).

cs.CV↗

arXiv2026

Inverse design of exceptional points in a single-resonance two-port network

Exceptional points (EPs) in non-Hermitian photonic systems enable unconventional control of wave amplitude and phase. However, identifying the EPs in a multidimensional parameter space of a system can be nontrivial and, in some cases, even infeasible. Here we propose an inverse-design method to efficiently locate the scattering EPs for a two-port resonant system supporting a single mode. The proposed method provides a direct way for tuning of geometric parameters to realize scattering EPs, as confirmed by both full-wave simulation and equivalent circuit model. In principle, our method is compatible with multi-mode system and applicable to a broad class of resonant systems.

physics.optics↗

arXiv2026

Asymptotically Optimal Quantum Universal Quickest Change Detection

This paper investigates the quickest change detection of quantum states in a universal setting: specifically, where the post-change quantum state is not known a priori. We establish the asymptotic optimality of a two-stage approach in terms of worst average delay to detection. The first stage employs block POVMs with classical outputs that preserve quantum relative entropy to arbitrary precision. The second stage leverages a recently proposed windowed-CUSUM algorithm that is known to be asymptotically optimal for quickest change detection with an unknown post-change distribution in the classical setting.

quant-ph↗

arXiv2026

Physics-Informed Chebyshev Polynomial Neural Operator for Parametric Partial Differential Equations

Neural operators have emerged as powerful deep learning frameworks for approximating solution operators of parameterized partial differential equations (PDE). However, current methods predominantly rely on multilayer perceptrons (MLPs) for mapping inputs to solutions, which impairs training robustness in physics-informed settings due to inherent spectral biases and fixed activation functions. To overcome the architectural limitations, we introduce the Physics-Informed Chebyshev Polynomial Neural Operator (CPNO), a novel mesh-free framework that leverages a basis transformation to replace unstable monomial expansions with the numerically stable Chebyshev spectral basis. By integrating parameter dependent modulation mechanism to main net, CPNO constructs PDE solutions in a near-optimal functional space, decoupling the model from MLP-specific constraints and enhancing multi-scale representation. Theoretical analysis demonstrates the Chebyshev basis's near-minimax uniform approximation properties and superior conditioning, with Lebesgue constants growing logarithmically with degree, thereby mitigating spectral bias and ensuring stable gradient flow during optimization. Numerical experiments on benchmark parameterized PDEs show that CPNO achieves superior accuracy, faster convergence, and enhanced robustness to hyperparameters. The experiment of transonic airfoil flow has demonstrated the capability of CPNO in characterizing complex geometric problems.

physics.flu-dyn↗

arXiv2026

Asymptotically Optimal Tests for One- and Two-Sample Problems

In this work, we revisit the one- and two-sample testing problems: binary hypothesis testing in which one or both distributions are unknown. For the one-sample test, we provide a more streamlined proof of the asymptotic optimality of Hoeffding's likelihood ratio test, which is equivalent to the threshold test of the relative entropy between the empirical distribution and the nominal distribution. The new proof offers an intuitive interpretation and naturally extends to the two-sample test where we show that a similar form of Hoeffding's test, namely a threshold test of the relative entropy between the two empirical distributions is also asymptotically optimal. A strong converse for the two-sample test is also obtained.

cs.IT↗

arXiv2025

Dropout Prompt Learning: Towards Robust and Adaptive Vision-Language Models

Dropout is a widely used regularization technique which improves the generalization ability of a model by randomly dropping neurons. In light of this, we propose Dropout Prompt Learning, which aims for applying dropout to improve the robustness of the vision-language models. Different from the vanilla dropout, we apply dropout on the tokens of the textual and visual branches, where we evaluate the token significance considering both intra-modal context and inter-modal alignment, enabling flexible dropout probabilities for each token. Moreover, to maintain semantic alignment for general knowledge transfer while encouraging the diverse representations that dropout introduces, we further propose residual entropy regularization. Experiments on 15 benchmarks show our method's effectiveness in challenging scenarios like low-shot learning, long-tail classification, and out-of-distribution generalization. Notably, our method surpasses regularization-based methods including KgCoOp by 5.10% and PromptSRC by 2.13% in performance on base-to-novel generalization.

cs.CV↗

arXiv2025

Bayes-DIC Net: Estimating Digital Image Correlation Uncertainty with Bayesian Neural Networks

This paper introduces a novel method for generating high-quality Digital Image Correlation (DIC) dataset based on non-uniform B-spline surfaces. By randomly generating control point coordinates, we construct displacement fields that encompass a variety of realistic displacement scenarios, which are subsequently used to generate speckle pattern datasets. This approach enables the generation of a large-scale dataset that capture real-world displacement field situations, thereby enhancing the training and generalization capabilities of deep learning-based DIC algorithms. Additionally, we propose a novel network architecture, termed Bayes-DIC Net, which extracts information at multiple levels during the down-sampling phase and facilitates the aggregation of information across various levels through a single skip connection during the up-sampling phase. Bayes-DIC Net incorporates a series of lightweight convolutional blocks designed to expand the receptive field and capture rich contextual information while minimizing computational costs. Furthermore, by integrating appropriate dropout modules into Bayes-DIC Net and activating them during the network inference stage, Bayes-DIC Net is transformed into a Bayesian neural network. This transformation allows the network to provide not only predictive results but also confidence levels in these predictions when processing real unlabeled datasets. This feature significantly enhances the practicality and reliability of our network in real-world displacement field prediction tasks. Through these innovations, this paper offers new perspectives and methods for dataset generation and algorithm performance enhancement in the field of DIC.

cs.CV↗

arXiv2025

Spatial Filtering with Nonlocal Non-Hermitian Metasurfaces

Spatial filtering of optical fields has widespread applications ranging from beam shaping to optical information processing. However, conventional spatial filters are bulky and alignment-sensitive. Here, we present nonlocal non-Hermitian metasurfaces that can act as exceptionally effective optical spatial filters while being highly compact and insensitive to both lateral and longitudinal displacements. The metasurface design is based on a resonant waveguide grating in which radiative losses of the modes are tailored to realize a symmetry-protected bound state in the continuum in the middle of a non-Hermitian flat band. Using this design, we propose a compact spatial filtering device operating over an angular range of approximately 1 degree around normal incidence. In addition to being ultrathin and robust against translational misalignment, the proposed metasurfaces are easy to manufacture, which makes them an attractive alternative to conventional spatial filters, holding a potential to become a widely used optical component.

physics.optics↗

arXiv2025

LFR-PINO: A Layered Fourier Reduced Physics-Informed Neural Operator for Parametric PDEs

Physics-informed neural operators have emerged as a powerful paradigm for solving parametric partial differential equations (PDEs), particularly in the aerospace field, enabling the learning of solution operators that generalize across parameter spaces. However, existing methods either suffer from limited expressiveness due to fixed basis/coefficient designs, or face computational challenges due to the high dimensionality of the parameter-to-weight mapping space. We present LFR-PINO, a novel physics-informed neural operator that introduces two key innovations: (1) a layered hypernetwork architecture that enables specialized parameter generation for each network layer, and (2) a frequency-domain reduction strategy that significantly reduces parameter count while preserving essential spectral features. This design enables efficient learning of a universal PDE solver through pre-training, capable of directly handling new equations while allowing optional fine-tuning for enhanced precision. The effectiveness of this approach is demonstrated through comprehensive experiments on four representative PDE problems, where LFR-PINO achieves 22.8%-68.7% error reduction compared to state-of-the-art baselines. Notably, frequency-domain reduction strategy reduces memory usage by 28.6%-69.3% compared to Hyper-PINNs while maintaining solution accuracy, striking an optimal balance between computational efficiency and solution fidelity.

cs.LG↗

arXiv2025

Towards Quantum Universal Hypothesis Testing

Hoeffding's formulation and solution to the universal hypothesis testing (UHT) problem had a profound impact on many subsequent works dealing with asymmetric hypotheses. In this work, we introduce a quantum universal hypothesis testing framework that serves as a quantum analog to Hoeffding's UHT. Motivated by Hoeffding's approach, which estimates the empirical distribution and uses it to construct the test statistic, we employ quantum state tomography to reconstruct the unknown state prior to forming the test statistic. Leveraging the concentration properties of quantum state tomography, we establish the exponential consistency of the proposed test: the type II error probability decays exponentially quickly, with the exponent determined by the trace distance between the true state and the nominal state.

cs.IT↗

arXiv2024

Toward End-to-End Bearing Fault Diagnosis for Industrial Scenarios with Spiking Neural Networks

This paper explores the application of spiking neural networks (SNNs), known for their low-power binary spikes, to bearing fault diagnosis, bridging the gap between high-performance AI algorithms and real-world industrial scenarios. In particular, we identify two key limitations of existing SNN fault diagnosis methods: inadequate encoding capacity that necessitates cumbersome data preprocessing, and non-spike-oriented architectures that constrain the performance of SNNs. To alleviate these problems, we propose a Multi-scale Residual Attention SNN (MRA-SNN) to simultaneously improve the efficiency, performance, and robustness of SNN methods. By incorporating a lightweight attention mechanism, we have designed a multi-scale attention encoding module to extract multiscale fault features from vibration signals and encode them as spatio-temporal spikes, eliminating the need for complicated preprocessing. Then, the spike residual attention block extracts high-dimensional fault features and enhances the expressiveness of sparse spikes with the attention mechanism for end-to-end diagnosis. In addition, the performance and robustness of MRA-SNN is further enhanced by introducing the lightweight attention mechanism within the spiking neurons to simulate the biological dendritic filtering effect. Extensive experiments on MFPT, JNU, Bearing, and Gearbox benchmark datasets demonstrate that MRA-SNN significantly outperforms existing methods in terms of accuracy, energy consumption, and noise robustness, and is more feasible for deployment in real-world industrial scenarios.

cs.NE↗

arXiv2024

Divergence Maximizing Linear Projection for Supervised Dimension Reduction

This paper proposes two linear projection methods for supervised dimension reduction using only the first and second-order statistics. The methods, each catering to a different parameter regime, are derived under the general Gaussian model by maximizing the Kullback-Leibler divergence between the two classes in the projected sample for a binary classification problem. They subsume existing linear projection approaches developed under simplifying assumptions of Gaussian distributions, such as these distributions might share an equal mean or covariance matrix. As a by-product, we establish that the multi-class linear discriminant analysis, a celebrated method for classification and supervised dimension reduction, is provably optimal for maximizing pairwise Kullback-Leibler divergence when the Gaussian populations share an identical covariance matrix. For the case when the Gaussian distributions share an equal mean, we establish conditions under which the optimal subspace remains invariant regardless of how the Kullback-Leibler divergence is defined, despite the asymmetry of the divergence measure itself. Such conditions encompass the classical case of signal plus noise, where both the signal and noise have zero mean and arbitrary covariance matrices. Experiments are conducted to validate the proposed solutions, demonstrate their superior performance over existing alternatives, and illustrate the procedure for selecting the appropriate linear projection solution.

cs.IT↗

arXiv2024

Three-dimensional angular deviation and diffraction efficiency of a grating in Littrow-configuration ECDL

We consider in this paper the angular deviation and diffraction efficiency of the reflection gratings in Littrow-configuration for applications of external cavity diode laser using the rigorous coupled-wave analysis method. We consider the three-dimensional diffraction case in general, where the incidence plane is un-parallel with the grating vector, i.e. conical diffraction. The angular tolerance of arbitrary gratings under plane and conical diffraction are thus derived and presented. A typical blazed grating is chosen as an example to calculate its diffraction efficiency using the rigorous coupled-wave analysis method. Furthermore, we point out that the angular tolerance and reflection efficiency can be improved if the appropriate parameter settings are selected for Littrow-configuration devices, including incidence angle, diffraction order, grating period and blazed angle. Otherwise, a tiny slanting angle of the grating vector deviated from the incidence plane will deviate the feedback light away from entering the laser-diode-chip and halt laser oscillation in the external cavity. Finally, a general rule for the parameter settings in Littrow-configuration is provided as a benchmark.

physics.optics↗

arXiv2021

Asymptotically Optimal One- and Two-Sample Testing with Kernels

We characterize the asymptotic performance of nonparametric one- and two-sample testing. The exponential decay rate or error exponent of the type-II error probability is used as the asymptotic performance metric, and an optimal test achieves the maximum rate subject to a constant level constraint on the type-I error probability. With Sanov's theorem, we derive a sufficient condition for one-sample tests to achieve the optimal error exponent in the universal setting, i.e., for any distribution defining the alternative hypothesis. We then show that two classes of Maximum Mean Discrepancy (MMD) based tests attain the optimal type-II error exponent on $\mathbb R^d$, while the quadratic-time Kernel Stein Discrepancy (KSD) based tests achieve this optimality with an asymptotic level constraint. For general two-sample testing, however, Sanov's theorem is insufficient to obtain a similar sufficient condition. We proceed to establish an extended version of Sanov's theorem and derive an exact error exponent for the quadratic-time MMD based two-sample tests. The obtained error exponent is further shown to be optimal among all two-sample tests satisfying a given level constraint. Our work hence provides an achievability result for optimal nonparametric one- and two-sample testing in the universal setting. Application to off-line change detection and related issues are also discussed.

cs.IT↗

arXiv2020

Harvesting Ambient RF for Presence Detection Through Deep Learning

This paper explores the use of ambient radio frequency (RF) signals for human presence detection through deep learning. Using WiFi signal as an example, we demonstrate that the channel state information (CSI) obtained at the receiver contains rich information about the propagation environment. Through judicious pre-processing of the estimated CSI followed by deep learning, reliable presence detection can be achieved. Several challenges in passive RF sensing are addressed. With presence detection, how to collect training data with human presence can have a significant impact on the performance. This is in contrast to activity detection when a specific motion pattern is of interest. A second challenge is that RF signals are complex-valued. Handling complex-valued input in deep learning requires careful data representation and network architecture design. Finally, human presence affects CSI variation along multiple dimensions; such variation, however, is often masked by system impediments such as timing or frequency offset. Addressing these challenges, the proposed learning system uses pre-processing to preserve human motion induced channel variation while insulating against other impairments. A convolutional neural network (CNN) properly trained with both magnitude and phase information is then designed to achieve reliable presence detection. Extensive experiments are conducted. Using off-the-shelf WiFi devices, the proposed deep learning based RF sensing achieves near perfect presence detection during multiple extended periods of test and exhibits superior performance compared with leading edge passive infrared sensors. Comparison with existing RF based human presence detection also demonstrates its robustness in performance, especially when deployed in a completely new environment.

cs.LG↗

arXiv2020

FOCUS: Dealing with Label Quality Disparity in Federated Learning

Ubiquitous systems with End-Edge-Cloud architecture are increasingly being used in healthcare applications. Federated Learning (FL) is highly useful for such applications, due to silo effect and privacy preserving. Existing FL approaches generally do not account for disparities in the quality of local data labels. However, the clients in ubiquitous systems tend to suffer from label noise due to varying skill-levels, biases or malicious tampering of the annotators. In this paper, we propose Federated Opportunistic Computing for Ubiquitous Systems (FOCUS) to address this challenge. It maintains a small set of benchmark samples on the FL server and quantifies the credibility of the client local data without directly observing them by computing the mutual cross-entropy between performance of the FL model on the local datasets and that of the client local FL model on the benchmark dataset. Then, a credit weighted orchestration is performed to adjust the weight assigned to clients in the FL model based on their credibility values. FOCUS has been experimentally evaluated on both synthetic data and real-world data. The results show that it effectively identifies clients with noisy labels and reduces their impact on the model performance, thereby significantly outperforming existing FL approaches.

cs.LG↗

arXiv2019

A practicable guide to the quantum computation architectures

The primordial model of quantum computation was introduced over thirty years ago and the first quantum algorithms have appeared for over twenty years. Yet the exact architectures for quantum computer seem foreign to an undergraduate student major in computer science or engineering, even though the mass media has helped popularize the terminologies in the past decade. Despite being a cutting-edge technology from both the theoretical and the experimental perspectives, quantum computation is indeed imminent and it would be helpful to give the undergraduate students at least a skeleton understanding of what a quantum computer stands for. Since instruction-set architectures originated from classical computing models are familiar, we propose analogously a set of quantum instructions, which can be composed to implement renowned quantum algorithms. Albeit the similarity one can draw between classical and quantum computer architectures, current quantum instructions are fundamentally incommensurable from their classical counterparts because they lack the innate capability to implement logical deductions and recursions. We discuss this trait in length and illustrate why it is held responsible that current quantum computers not be considered general computers.

quant-ph↗

arXiv2019

Universal Hypothesis Testing with Kernels: Asymptotically Optimal Tests for Goodness of Fit

We characterize the asymptotic performance of nonparametric goodness of fit testing. The exponential decay rate of the type-II error probability is used as the asymptotic performance metric, and a test is optimal if it achieves the maximum rate subject to a constant level constraint on the type-I error probability. We show that two classes of Maximum Mean Discrepancy (MMD) based tests attain this optimality on $\mathbb R^d$, while the quadratic-time Kernel Stein Discrepancy (KSD) based tests achieve the maximum exponential decay rate under a relaxed level constraint. Under the same performance metric, we proceed to show that the quadratic-time MMD based two-sample tests are also optimal for general two-sample problems, provided that kernels are bounded continuous and characteristic. Key to our approach are Sanov's theorem from large deviation theory and the weak metrizable properties of the MMD and KSD.

stat.ML↗