arXiv subjects

Yanli Li

Publications and source records attributed to Yanli Li.

18 recordsLinked to original sources

arXiv2026

mmRadarTwin: A Measurement-Calibrated Signal-Level Digital Twin Platform for Indoor mmWave Radar

Indoor mmWave radar perception is difficult to reproduce because measured range-angle responses depend on scene geometry, material response, multipath, hardware conventions, and signal processing. Existing ray-tracing and digital-twin tools often expose rendering, channel, or path-level quantities, while radar sensing requires complex signal products that can be processed and compared in the same domain as real FMCW measurements. We present mmRadarTwin, a signal-level and path-attributed digital-twin platform for indoor mmWave radar. mmRadarTwin links a real radar measurement branch with an Unreal Engine scene-simulation branch through a shared receive-channel and range-angle processing interface. The simulator writes complex multi-channel receive grids and exports per-path contribution records that identify the actor, material tag, propagation event, and output-bin support of each simulated return. We evaluate mmRadarTwin in an office deployment using a commodity monostatic mmWave radar and mobile scene-capture hardware. Across 154 measured poses spanning 22 radar locations, the current physics-only path-basis simulator recalls 70.8% of measurement-active geometry-supported response regions in the central usable field of view while exposing residuals caused by weak or missing path support, shifted responses, unsupported anchors, and missing physical mechanisms. Rather than claiming complete radar-map reconstruction or cross-room generalization, mmRadarTwin establishes a practical systems workflow for constructing, comparing, and diagnosing indoor radar digital twins.

cs.CV↗

arXiv2026

PoseCompass: Intelligent Synthetic Pose Selection for Visual Localization

In visual localization, Absolute Pose Regression (APR) enables real-time 6-DoF camera pose inference from single images, yet critically depends on fine-tuning data quality and coverage. While recent methods leverage 3D Gaussian Splatting (3DGS) for novel view synthesis-based data augmentation, random sampling generates redundant views and noisy samples from poorly reconstructed regions. To mitigate this research gap, we propose PoseCompass, an intelligent pose selection pipeline for 3DGS-based APR. PoseCompass formulates synthetic pose selection and derives a value-based pose ranking mechanism to identify informative poses. The ranking integrates three dimensions: Localization Difficulty, favoring challenging regions; Coverage Novelty, exploring under-sampled areas; and Rendering Observability, filtering artifacts and noise. PoseCompass then generates trajectory-constrained candidates, selects the top-K ranked poses, and synthesizes views using 3DGS with lightweight diffusion-based alignment. Finally, the pose regressor is fine-tuned on mixed real and synthetic data. We evaluate PoseCompass on 7-Scenes, where it reduces adaptation time from 15.2 to 5.1 minutes, a 3x speedup, while cutting median pose errors by 53.8 percent and significantly outperforming random baselines.

cs.CV↗

arXiv2025

Optimal Look-back Horizon for Time Series Forecasting in Federated Learning

Selecting an appropriate look-back horizon remains a fundamental challenge in time series forecasting (TSF), particularly in the federated learning scenarios where data is decentralized, heterogeneous, and often non-independent. While recent work has explored horizon selection by preserving forecasting-relevant information in an intrinsic space, these approaches are primarily restricted to centralized and independently distributed settings. This paper presents a principled framework for adaptive horizon selection in federated time series forecasting through an intrinsic space formulation. We introduce a synthetic data generator (SDG) that captures essential temporal structures in client data, including autoregressive dependencies, seasonality, and trend, while incorporating client-specific heterogeneity. Building on this model, we define a transformation that maps time series windows into an intrinsic representation space with well-defined geometric and statistical properties. We then derive a decomposition of the forecasting loss into a Bayesian term, which reflects irreducible uncertainty, and an approximation term, which accounts for finite-sample effects and limited model capacity. Our analysis shows that while increasing the look-back horizon improves the identifiability of deterministic patterns, it also increases approximation error due to higher model complexity and reduced sample efficiency. We prove that the total forecasting loss is minimized at the smallest horizon where the irreducible loss starts to saturate, while the approximation loss continues to rise. This work provides a rigorous theoretical foundation for adaptive horizon selection for time series forecasting in federated learning.

cs.LG↗

arXiv2025

GuardFed: A Trustworthy Federated Learning Framework Against Dual-Facet Attacks

Federated learning (FL) enables privacy-preserving collaborative model training but remains vulnerable to adversarial behaviors that compromise model utility or fairness across sensitive groups. While extensive studies have examined attacks targeting either objective, strategies that simultaneously degrade both utility and fairness remain largely unexplored. To bridge this gap, we introduce the Dual-Facet Attack (DFA), a novel threat model that concurrently undermines predictive accuracy and group fairness. Two variants, Synchronous DFA (S-DFA) and Split DFA (Sp-DFA), are further proposed to capture distinct real-world collusion scenarios. Experimental results show that existing robust FL defenses, including hybrid aggregation schemes, fail to resist DFAs effectively. To counter these threats, we propose GuardFed, a self-adaptive defense framework that maintains a fairness-aware reference model using a small amount of clean server data augmented with synthetic samples. In each training round, GuardFed computes a dual-perspective trust score for every client by jointly evaluating its utility deviation and fairness degradation, thereby enabling selective aggregation of trustworthy updates. Extensive experiments on real-world datasets demonstrate that GuardFed consistently preserves both accuracy and fairness under diverse non-IID and adversarial conditions, achieving state-of-the-art performance compared with existing robust FL methods.

cs.LG↗

arXiv2025

DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance

Large Language Models (LLMs) are increasingly deployed as Internet/Web services (LLM-as-a-Service) with strict latency Service-Level Objectives (SLOs) under tight GPU memory budgets. Mixture-of-Experts (MoE) models improve quality and throughput via sparse expert activation, but serving them efficiently is challenging because expert weights dominate memory footprint and incur costly host--device transfers when offloaded. Moreover, MoE serving exhibits a phase disparity: the prefill phase tends to activate experts densely across many tokens, while the decode phase activates only a few experts per step. A uniform expert loading/caching policy across phases leads to either peak-memory blowup (prefill) or tail-latency inflation (decode). We present DuoServe-MoE, a QoS-oriented MoE serving system that decouples prefill and decode and applies phase-specialized expert scheduling. For prefill, DuoServe-MoE uses a two-stream CUDA pipeline to overlap expert prefetching with non-MoE computation, reducing expert residency time and peak GPU memory. For decode, it employs a lightweight layer-level predictor trained offline from activation traces to prefetch only likely experts without model changes. Experiments on representative MoE LLMs show that DuoServe-MoE improves TTFT by up to $5.34\times$ and end-to-end latency by up to $7.55\times$ over representative baselines, while maintaining low runtime GPU memory usage under resource-constrained deployment.

cs.DC↗

arXiv2025

Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systems

Adversarial attacks against computer vision systems have emerged as a critical research area that challenges the fundamental assumptions about neural network robustness and security. This comprehensive survey examines the evolving landscape of adversarial techniques, revealing their dual nature as both sophisticated security threats and valuable defensive tools. We provide a systematic analysis of adversarial attack methodologies across three primary domains: pixel-space attacks, physically realizable attacks, and latent-space attacks. Our investigation traces the technical evolution from early gradient-based methods such as FGSM and PGD to sophisticated optimization techniques incorporating momentum, adaptive step sizes, and advanced transferability mechanisms. We examine how physically realizable attacks have successfully bridged the gap between digital vulnerabilities and real-world threats through adversarial patches, 3D textures, and dynamic optical perturbations. Additionally, we explore the emergence of latent-space attacks that leverage semantic structure in internal representations to create more transferable and meaningful adversarial examples. Beyond traditional offensive applications, we investigate the constructive use of adversarial techniques for vulnerability assessment in biometric authentication systems and protection against malicious generative models. Our analysis reveals critical research gaps, particularly in neural style transfer protection and computational efficiency requirements. This survey contributes a comprehensive taxonomy, evolution analysis, and identification of future research directions, aiming to advance understanding of adversarial vulnerabilities and inform the development of more robust and trustworthy computer vision systems.

cs.CV↗

arXiv2025

Beam single spin asymmetry $A_{LU}^{\sin \phi_R}$ of the dihadron production in SIDIS process

We study the longitudinal beam single-spin asymmetry $A_{LU}^{\sin \phi_R}$ of dihadron production in semi-inclusive deep inelastic scattering process with a polarized electron beam scattering off an unpolarized proton target. The asymmetry arises from the convolutions of twist-3 PDF $e(x)$ and twist-2 DiFF $H_1^\sphericalangle$ as well as twist-2 PDF $f_1(x)$ and twist-3 DiFF $\widetilde{G}^{\sphericalangle}$. Using the spectator model calculations for the twist-3 PDF $e(x)$, the DiFFs $D_1 , H_1^\sphericalangle$, and $\widetilde{G}^{\sphericalangle}$, we estimate the BSA $A^{\sin \phi_R}_{LU}$ at the kinematical configuration of CLAS and CLAS12. We find good agreement with $z$- and $M_h$-dependencies data, though $x$- and $Q^2$- dependencies show discrepancies. We include DGLAP evolution of $e(x)$ and provide predictions for COMPASS, EIC, and EicC. The negligible contribution from $f_1(x) \otimes \widetilde{G}^{\sphericalangle}$ supports the Wandzura-Wilczek approximation, while our results highlight the importance of QCD evolution in twist-3 PDF analyses.

hep-ph↗

arXiv2025

Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detection

As a special type of multimedia data, Lithography Hotspot Detection (LHD) training often requires stronger privacy protection than conventional multimedia data, and federated learning provides a promising potential solution to this challenge. However, existing approaches rely solely on either parameter aggregation or Knowledge Distillation (KD), failing to fully exploit the potential of collaborative learning. To address this, we propose FedKD-hybrid, a novel framework that synergizes the strengths of both paradigms. Specifically, FedKD-hybrid utilizes a public dataset to facilitate consensus, where clients exchange both parameters of agreed-upon layers and logits. This hybrid information is aggregated to refine local models, enhancing knowledge transfer. Extensive experiments on ICCAD-2012 and real-world FAB datasets demonstrate that FedKD-hybrid consistently outperforms state-of-the-art methods in both effectiveness and robustness.

cs.LG↗

arXiv2024

Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges

Federated Learning (FL) offers innovative solutions for privacy-preserving collaborative machine learning (ML). Despite its promising potential, FL is vulnerable to various attacks due to its distributed nature, affecting the entire life cycle of FL services. These threats can harm the model's utility or compromise participants' privacy, either directly or indirectly. In response, numerous defense frameworks have been proposed, demonstrating effectiveness in specific settings and scenarios. To provide a clear understanding of the current research landscape, this paper reviews the most representative and state-of-the-art threats and defense frameworks throughout the FL service life cycle. We start by identifying FL threats that harm utility and privacy, including those with potential or direct impacts. Then, we dive into the defense frameworks, analyze the relationship between threats and defenses, and compare the trade-offs among different defense strategies. Finally, we summarize current research bottlenecks and offer insights into future research directions to conclude this survey. We hope this survey sheds light on trustworthy FL research and contributes to the FL community.

cs.DC↗

arXiv2024

Integrated feature analysis for deep learning interpretation and class activation maps

Understanding the decisions of deep learning (DL) models is essential for the acceptance of DL to risk-sensitive applications. Although methods, like class activation maps (CAMs), give a glimpse into the black box, they do miss some crucial information, thereby limiting its interpretability and merely providing the considered locations of objects. To provide more insight into the models and the influence of datasets, we propose an integrated feature analysis method, which consists of feature distribution analysis and feature decomposition, to look closer into the intermediate features extracted by DL models. This integrated feature analysis could provide information on overfitting, confounders, outliers in datasets, model redundancies and principal features extracted by the models, and provide distribution information to form a common intensity scale, which are missing in current CAM algorithms. The integrated feature analysis was applied to eight different datasets for general validation: photographs of handwritten digits, two datasets of natural images and five medical datasets, including skin photography, ultrasound, CT, X-rays and MRIs. The method was evaluated by calculating the consistency between the CAMs average class activation levels and the logits of the model. Based on the eight datasets, the correlation coefficients through our method were all very close to 100%, and based on the feature decomposition, 5%-25% of features could generate equally informative saliency maps and obtain the same model performances as using all features. This proves the reliability of the integrated feature analysis. As the proposed methods rely on very few assumptions, this is a step towards better model interpretation and a useful extension to existing CAM algorithms. Codes: https://github.com/YanliLi27/IFA

cs.CV↗

arXiv2024

Holistic Evaluation Metrics: Use Case Sensitive Evaluation Metrics for Federated Learning

A large number of federated learning (FL) algorithms have been proposed for different applications and from varying perspectives. However, the evaluation of such approaches often relies on a single metric (e.g., accuracy). Such a practice fails to account for the unique demands and diverse requirements of different use cases. Thus, how to comprehensively evaluate an FL algorithm and determine the most suitable candidate for a designated use case remains an open question. To mitigate this research gap, we introduce the Holistic Evaluation Metrics (HEM) for FL in this work. Specifically, we collectively focus on three primary use cases, which are Internet of Things (IoT), smart devices, and institutions. The evaluation metric encompasses various aspects including accuracy, convergence, computational efficiency, fairness, and personalization. We then assign a respective importance vector for each use case, reflecting their distinct performance requirements and priorities. The HEM index is finally generated by integrating these metric components with their respective importance vectors. Through evaluating different FL algorithms in these three prevalent use cases, our experimental results demonstrate that HEM can effectively assess and identify the FL algorithms best suited to particular scenarios. We anticipate this work sheds light on the evaluation process for pragmatic FL algorithms in real-world applications.

cs.LG↗

arXiv2024

Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack

Neural style transfer (NST) generates new images by combining the style of one image with the content of another. However, unauthorized NST can exploit artwork, raising concerns about artists' rights and motivating the development of proactive protection methods. We propose Locally Adaptive Adversarial Color Attack (LAACA), empowering artists to protect their artwork from unauthorized style transfer by processing before public release. By delving into the intricacies of human visual perception and the role of different frequency components, our method strategically introduces frequency-adaptive perturbations in the image. These perturbations significantly degrade the generation quality of NST while maintaining an acceptable level of visual change in the original image, ensuring that potential infringers are discouraged from using the protected artworks, because of its bad NST generation quality. Additionally, existing metrics often overlook the importance of color fidelity in evaluating color-mattered tasks, such as the quality of NST-generated images, which is crucial in the context of artistic works. To comprehensively assess the color-mattered tasks, we propose the Adversarial Color Distance Metric (ACDM), designed to quantify the color difference of images pre- and post-manipulations. Experimental results confirm that attacking NST using LAACA results in visually inferior style transfer, and the ACDM can efficiently measure color-mattered tasks. By providing artists with a tool to safeguard their intellectual property, our work relieves the socio-technical challenges posed by the misuse of NST in the art community.

cs.CV↗

arXiv2023

Honest Score Client Selection Scheme: Preventing Federated Learning Label Flipping Attacks in Non-IID Scenarios

Federated Learning (FL) is a promising technology that enables multiple actors to build a joint model without sharing their raw data. The distributed nature makes FL vulnerable to various poisoning attacks, including model poisoning attacks and data poisoning attacks. Today, many byzantine-resilient FL methods have been introduced to mitigate the model poisoning attack, while the effectiveness when defending against data poisoning attacks still remains unclear. In this paper, we focus on the most representative data poisoning attack - "label flipping attack" and monitor its effectiveness when attacking the existing FL methods. The results show that the existing FL methods perform similarly in Independent and identically distributed (IID) settings but fail to maintain the model robustness in Non-IID settings. To mitigate the weaknesses of existing FL methods in Non-IID scenarios, we introduce the Honest Score Client Selection (HSCS) scheme and the corresponding HSCSFL framework. In the HSCSFL, The server collects a clean dataset for evaluation. Under each iteration, the server collects the gradients from clients and then perform HSCS to select aggregation candidates. The server first evaluates the performance of each class of the global model and generates the corresponding risk vector to indicate which class could be potentially attacked. Similarly, the server evaluates the client's model and records the performance of each class as the accuracy vector. The dot product of each client's accuracy vector and global risk vector is generated as the client's host score; only the top p\% host score clients are included in the following aggregation. Finally, server aggregates the gradients and uses the outcome to update the global model. The comprehensive experimental results show our HSCSFL effectively enhances the FL robustness and defends against the "label flipping attack."

cs.CR↗

arXiv2023

Quantum-Enhanced Forecasting: Leveraging Quantum Gramian Angular Field and CNNs for Stock Return Predictions

We propose a time series forecasting method named Quantum Gramian Angular Field (QGAF). This approach merges the advantages of quantum computing technology with deep learning, aiming to enhance the precision of time series classification and forecasting. We successfully transformed stock return time series data into two-dimensional images suitable for Convolutional Neural Network (CNN) training by designing specific quantum circuits. Distinct from the classical Gramian Angular Field (GAF) approach, QGAF's uniqueness lies in eliminating the need for data normalization and inverse cosine calculations, simplifying the transformation process from time series data to two-dimensional images. To validate the effectiveness of this method, we conducted experiments on datasets from three major stock markets: the China A-share market, the Hong Kong stock market, and the US stock market. Experimental results revealed that compared to the classical GAF method, the QGAF approach significantly improved time series prediction accuracy, reducing prediction errors by an average of 25% for Mean Absolute Error (MAE) and 48% for Mean Squared Error (MSE). This research confirms the potential and promising prospects of integrating quantum computing with deep learning techniques in financial time series forecasting.

cs.LG↗

arXiv2020

How the emotion's type and intensity affect rumor spreading

The implication and contagion effect of emotion cannot be ignored in rumor spreading. This paper sheds light on how DMs'emotional type and intensity affect rumor spreading. Based on the theory of RDEU and evolutionary game, we construct an evolutionary game model of rumor spreading by considering emotions, which takes netizens and the government as the core subjects. Through MATLAB to simulate and reveal the influencing mechanism of DMs'emotional type and intensity on rumor spreading. The results indicate that the DMs'choice of strategy is not only affected by their own emotional preference and intensity but also affected by that of the other player in rumor spreading. Pessimism has a more significant influence on the stability of the evolutionary game than optimism, the government's emotion types are more sensitive to the game results than netizens, and the emotional intensity is proportional to the evolution speed. More importantly, some significant emotional thresholds are found, which can be used to predict the behavior of netizens, helping the government gain critical time to deal with rumors and avoid the Tacitus Trap crisis. Furthermore, the simulation results are summarized as five types: risk, opportunity, ideal, security, and opposition. We hope that this work is beneficial to the government's public governance.

cs.SI↗

arXiv2012

Donor and acceptor levels of organic photovoltaic compounds from first principles

Accurate and efficient approaches to predict the optical properties of organic semiconducting compounds could accelerate the search for efficient organic photovoltaic materials. Nevertheless, predicting the optical properties of organic semiconductors has been plagued by the inaccuracy or computational cost of conventional first-principles calculations. In this work, we demonstrate that orbital-dependent density-functional theory based upon Koopmans' condition [Phys. Rev. B 82, 115121 (2010)] is apt at describing donor and acceptor levels for a wide variety of organic molecules, clusters, and oligomers within a few tenths of an electron-volt relative to experiment, which is comparable to the predictive performance of many-body perturbation theory methods at a fraction of the computational cost.

cond-mat.mtrl-sci↗

arXiv2011

Electronic levels and electrical response of periodic molecular structures from plane-wave orbital-dependent calculations

Plane-wave electronic-structure predictions based upon orbital-dependent density-functional theory (OD-DFT) approximations, such as hybrid density-functional methods and self-interaction density-functional corrections, are severely affected by computational inaccuracies in evaluating electron interactions in the plane-wave representation. These errors arise from divergence singularities in the plane-wave summation of electrostatic and exchange interaction contributions. Auxiliary-function corrections are reciprocal-space countercharge corrections that cancel plane-wave singularities through the addition of an auxiliary function to the point-charge electrostatic kernel that enters into the expression of interaction terms. At variance with real-space countercharge corrections that are employed in the context of density-functional theory (DFT), reciprocal-space corrections are computationally inexpensive, making them suited to more demanding OD-DFT calculations. Nevertheless, there exists much freedom in the choice of auxiliary functions and various definitions result in different levels of performance in eliminating plane-wave inaccuracies. In this work, we derive exact point-charge auxiliary functions for the description of molecular structures of arbitrary translational symmetry, including the yet unaddressed one-dimensional case. In addition, we provide a critical assessment of different reciprocal-space countercharge corrections and demonstrate the improved accuracy of point-charge auxiliary functions in predicting the electronic levels and electrical response of conjugated polymers from plane-wave OD-DFT calculations.

cond-mat.mtrl-sci↗

arXiv2010

Koopmans' condition for density-functional theory

In approximate Kohn-Sham density-functional theory, self-interaction manifests itself as the dependence of the energy of an orbital on its fractional occupation. This unphysical behavior translates into qualitative and quantitative errors that pervade many fundamental aspects of density-functional predictions. Here, we first examine self-interaction in terms of the discrepancy between total and partial electron removal energies, and then highlight the importance of imposing the generalized Koopmans' condition -- that identifies orbital energies as opposite total electron removal energies -- to resolve this discrepancy. In the process, we derive a correction to approximate functionals that, in the frozen-orbital approximation, eliminates the unphysical occupation dependence of orbital energies up to the third order in the single-particle densities. This non-Koopmans correction brings physical meaning to single-particle energies; when applied to common local or semilocal density functionals it provides results that are in excellent agreement with experimental data -- with an accuracy comparable to that of GW many-body perturbation theory -- while providing an explicit total energy functional that preserves or improves on the description of established structural properties.

cond-mat.mtrl-sci↗