arXiv subjects

Xingyu Li

Publications and source records attributed to Xingyu Li.

At least 109 records · Page 6Linked to original sources

arXiv2024

SISSA: Real-time Monitoring of Hardware Functional Safety and Cybersecurity with In-vehicle SOME/IP Ethernet Traffic

Scalable service-Oriented Middleware over IP (SOME/IP) is an Ethernet communication standard protocol in the Automotive Open System Architecture (AUTOSAR), promoting ECU-to-ECU communication over the IP stack. However, SOME/IP lacks a robust security architecture, making it susceptible to potential attacks. Besides, random hardware failure of ECU will disrupt SOME/IP communication. In this paper, we propose SISSA, a SOME/IP communication traffic-based approach for modeling and analyzing in-vehicle functional safety and cyber security. Specifically, SISSA models hardware failures with the Weibull distribution and addresses five potential attacks on SOME/IP communication, including Distributed Denial-of-Services, Man-in-the-Middle, and abnormal communication processes, assuming a malicious user accesses the in-vehicle network. Subsequently, SISSA designs a series of deep learning models with various backbones to extract features from SOME/IP sessions among ECUs. We adopt residual self-attention to accelerate the model's convergence and enhance detection accuracy, determining whether an ECU is under attack, facing functional failure, or operating normally. Additionally, we have created and annotated a dataset encompassing various classes, including indicators of attack, functionality, and normalcy. This contribution is noteworthy due to the scarcity of publicly accessible datasets with such characteristics.Extensive experimental results show the effectiveness and efficiency of SISSA.

cs.CR↗

arXiv2024

Non-Adiabatic Effect in Topological and Interacting Charge Pumping

Topological charge pumping occurs in the adiabatic limit, and the non-adiabatic effect due to finite ramping velocity reduces the pumping efficiency and leads to deviation from quantized charge pumping. In this work, we discuss the relation between this deviation from quantized charge pumping and the entanglement generation after a pumping circle. In the simplest setting, we show that purity $\mathcal{P}$ of the half system reduced density matrix equals to $\mathcal{R}$ defined as $(1-κ)^2+κ^2$, where $κ$ denotes the pumping efficiency. In generic situations, we argue $\mathcal{P}<\mathcal{R}$ and the pumping efficiency can provide an upper bound for purity and, therefore, a lower bound for generated entanglement. To support this conjecture, we propose a solvable pumping scheme in the Rice--Mele--Hubbard model, which can be represented as brick-wall type quantum circuit model. With this pumping scheme, numerical calculation of charge pumping only needs to include at most six sites, and therefore, the interaction and the finite temperature effects can be both included reliably in the exact diagonalization calculation. The numerical results using the solvable pumping circle identify two regimes where the pumping efficiency is sensitive to ramping velocity and support the conjecture $\mathcal{P}<\mathcal{R}$ when both interaction and finite temperature effects are present.

cond-mat.mes-hall↗

arXiv2024

An Investigation of Patch Porting Practices of the Linux Kernel Ecosystem

Open-source software is increasingly reused, complicating the process of patching to repair bugs. In the case of Linux, a distinct ecosystem has formed, with Linux mainline serving as the upstream, stable or long-term-support (LTS) systems forked from mainline, and Linux distributions, such as Ubuntu and Android, as downstreams forked from stable or LTS systems for end-user use. Ideally, when a patch is committed in the Linux upstream, it should not introduce new bugs and be ported to all the applicable downstream branches in a timely fashion. However, several concerns have been expressed in prior work about the responsiveness of patch porting in this Linux ecosystem. In this paper, we mine the software repositories to investigate a range of Linux distributions in combination with Linux stable and LTS, and find diverse patch porting strategies and competence levels that help explain the phenomenon. Furthermore, we show concretely using three metrics, i.e., patch delay, patch rate, and bug inheritance ratio, that different porting strategies have different tradeoffs. We find that hinting tags(e.g., Cc stable tags and fixes tags) are significantly important to the prompt patch porting, but it is noteworthy that a substantial portion of patches remain devoid of these indicative tags. Finally, we offer recommendations based on our analysis of the general patch flow, e.g., interactions among various stakeholders in the ecosystem and automatic generation of hinting tags, as well as tailored suggestions for specific porting strategies.

cs.SE↗

arXiv2024

Adaptive Confidence Multi-View Hashing for Multimedia Retrieval

The multi-view hash method converts heterogeneous data from multiple views into binary hash codes, which is one of the critical technologies in multimedia retrieval. However, the current methods mainly explore the complementarity among multiple views while lacking confidence learning and fusion. Moreover, in practical application scenarios, the single-view data contain redundant noise. To conduct the confidence learning and eliminate unnecessary noise, we propose a novel Adaptive Confidence Multi-View Hashing (ACMVH) method. First, a confidence network is developed to extract useful information from various single-view features and remove noise information. Furthermore, an adaptive confidence multi-view network is employed to measure the confidence of each view and then fuse multi-view features through a weighted summation. Lastly, a dilation network is designed to further enhance the feature representation of the fused features. To the best of our knowledge, we pioneer the application of confidence learning into the field of multimedia retrieval. Extensive experiments on two public datasets show that the proposed ACMVH performs better than state-of-the-art methods (maximum increase of 3.24%). The source code is available at https://github.com/HackerHyper/ACMVH.

cs.CV↗

arXiv2023

The Vlasov-Maxwell-Boltzmann/Landau system with polynomial perturbation near Maxwellian

In this paper, we study the Vlasov-Maxwell-Boltzmann system without angular cutoff and the Vlasov-Maxwell-Landau/Boltzmann system with polynomial perturbation $F=μ+f$ near global Maxwellian. In particular, we prove the global existence, uniqueness and large time behavior for solutions in a polynomial weighted space $H^N_{x,v}(\langle v\rangle^k)$. The method is based on Duhamel's principle with the crucial time-decay analysis on the particle distribution $f$ and the electromagnetic field $(E,B)$.

math.AP↗

arXiv2023

Global Contrast Masked Autoencoders Are Powerful Pathological Representation Learners

Based on digital pathology slice scanning technology, artificial intelligence algorithms represented by deep learning have achieved remarkable results in the field of computational pathology. Compared to other medical images, pathology images are more difficult to annotate, and thus, there is an extreme lack of available datasets for conducting supervised learning to train robust deep learning models. In this paper, we propose a self-supervised learning (SSL) model, the global contrast-masked autoencoder (GCMAE), which can train the encoder to have the ability to represent local-global features of pathological images, also significantly improve the performance of transfer learning across data sets. In this study, the ability of the GCMAE to learn migratable representations was demonstrated through extensive experiments using a total of three different disease-specific hematoxylin and eosin (HE)-stained pathology datasets: Camelyon16, NCTCRC and BreakHis. In addition, this study designed an effective automated pathology diagnosis process based on the GCMAE for clinical applications. The source code of this paper is publicly available at https://github.com/StarUniversus/gcmae.

eess.IV↗

arXiv2023

Improving Contrastive Learning of Sentence Embeddings with Focal-InfoNCE

The recent success of SimCSE has greatly advanced state-of-the-art sentence representations. However, the original formulation of SimCSE does not fully exploit the potential of hard negative samples in contrastive learning. This study introduces an unsupervised contrastive learning framework that combines SimCSE with hard negative mining, aiming to enhance the quality of sentence embeddings. The proposed focal-InfoNCE function introduces self-paced modulation terms in the contrastive objective, downweighting the loss associated with easy negatives and encouraging the model focusing on hard negatives. Experimentation on various STS benchmarks shows that our method improves sentence embeddings in terms of Spearman's correlation and representation alignment and uniformity.

cs.CL↗

arXiv2023

Text-driven Prompt Generation for Vision-Language Models in Federated Learning

Prompt learning for vision-language models, e.g., CoOp, has shown great success in adapting CLIP to different downstream tasks, making it a promising solution for federated learning due to computational reasons. Existing prompt learning techniques replace hand-crafted text prompts with learned vectors that offer improvements on seen classes, but struggle to generalize to unseen classes. Our work addresses this challenge by proposing Federated Text-driven Prompt Generation (FedTPG), which learns a unified prompt generation network across multiple remote clients in a scalable manner. The prompt generation network is conditioned on task-related text input, thus is context-aware, making it suitable to generalize for both seen and unseen classes. Our comprehensive empirical evaluations on nine diverse image classification datasets show that our method is superior to existing federated prompt learning methods, that achieve overall better generalization on both seen and unseen classes and is also generalizable to unseen datasets.

cs.CV↗

arXiv2023

Reviving the Lieb-Schultz-Mattis Theorem in Open Quantum Systems

In closed systems, the celebrated Lieb-Schultz-Mattis (LSM) theorem states that a one-dimensional locally interacting half-integer spin chain with translation and spin rotation symmetry cannot have a non-degenerate gapped ground state. However, the applicability of this theorem is diminished when the system interacts with a bath and loses its energy conservation. In this letter, we propose that the LSM theorem can be revived in the entanglement Hamiltonian when the coupling to bath renders the system short-range correlated. Specifically, we argue that the entanglement spectrum cannot have a non-degenerate minimum, isolated by a gap from other states. We further support the results with numerical examples where a spin-$1/2$ system is coupled to another spin-$3/2$ chain serving as the bath. Compared with the original LSM theorem which primarily addresses UV--IR correspondence, our findings unveil that the UV data and topological constraints also have a pivotal role in shaping the entanglement in open quantum many-body systems.

cond-mat.str-el↗

arXiv2023

Advancing Adversarial Robustness Through Adversarial Logit Update

Deep Neural Networks are susceptible to adversarial perturbations. Adversarial training and adversarial purification are among the most widely recognized defense strategies. Although these methods have different underlying logic, both rely on absolute logit values to generate label predictions. In this study, we theoretically analyze the logit difference around successful adversarial attacks from a theoretical point of view and propose a new principle, namely Adversarial Logit Update (ALU), to infer adversarial sample's labels. Based on ALU, we introduce a new classification paradigm that utilizes pre- and post-purification logit differences for model's adversarial robustness boost. Without requiring adversarial or additional data for model training, our clean data synthesis model can be easily applied to various pre-trained models for both adversarial sample detection and ALU-based data classification. Extensive experiments on both CIFAR-10, CIFAR-100, and tiny-ImageNet datasets show that even with simple components, the proposed solution achieves superior robustness performance compared to state-of-the-art methods against a wide range of adversarial attacks. Our python implementation is submitted in our Supplementary document and will be published upon the paper's acceptance.

cs.LG↗

arXiv2023

Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning

There emerges a promising trend of using large language models (LLMs) to generate code-like plans for complex inference tasks such as visual reasoning. This paradigm, known as LLM-based planning, provides flexibility in problem solving and endows better interpretability. However, current research is mostly limited to basic scenarios of simple questions that can be straightforward answered in a few inference steps. Planning for the more challenging multi-hop visual reasoning tasks remains under-explored. Specifically, under multi-hop reasoning situations, the trade-off between accuracy and the complexity of plan-searching becomes prominent. The prevailing algorithms either address the efficiency issue by employing the fast one-stop generation or adopt a complex iterative generation method to improve accuracy. Both fail to balance the need for efficiency and performance. Drawing inspiration from the dual system of cognition in the human brain, the fast and the slow think processes, we propose a hierarchical plan-searching algorithm that integrates the one-stop reasoning (fast) and the Tree-of-thought (slow). Our approach succeeds in performance while significantly saving inference steps. Moreover, we repurpose the PTR and the CLEVER datasets, developing a systematic framework for evaluating the performance and efficiency of LLMs-based plan-search algorithms under reasoning tasks at different levels of difficulty. Extensive experiments demonstrate the superiority of our proposed algorithm in terms of performance and efficiency. The dataset and code will be release soon.

cs.CL↗

arXiv2023

G-Mix: A Generalized Mixup Learning Framework Towards Flat Minima

Deep neural networks (DNNs) have demonstrated promising results in various complex tasks. However, current DNNs encounter challenges with over-parameterization, especially when there is limited training data available. To enhance the generalization capability of DNNs, the Mixup technique has gained popularity. Nevertheless, it still produces suboptimal outcomes. Inspired by the successful Sharpness-Aware Minimization (SAM) approach, which establishes a connection between the sharpness of the training loss landscape and model generalization, we propose a new learning framework called Generalized-Mixup, which combines the strengths of Mixup and SAM for training DNN models. The theoretical analysis provided demonstrates how the developed G-Mix framework enhances generalization. Additionally, to further optimize DNN performance with the G-Mix framework, we introduce two novel algorithms: Binary G-Mix and Decomposed G-Mix. These algorithms partition the training data into two subsets based on the sharpness-sensitivity of each example to address the issue of "manifold intrusion" in Mixup. Both theoretical explanations and experimental results reveal that the proposed BG-Mix and DG-Mix algorithms further enhance model generalization across multiple datasets and models, achieving state-of-the-art performance.

cs.LG↗

arXiv2023

AdaER: An Adaptive Experience Replay Approach for Continual Lifelong Learning

Continual lifelong learning is an machine learning framework inspired by human learning, where learners are trained to continuously acquire new knowledge in a sequential manner. However, the non-stationary nature of streaming training data poses a significant challenge known as catastrophic forgetting, which refers to the rapid forgetting of previously learned knowledge when new tasks are introduced. While some approaches, such as experience replay (ER), have been proposed to mitigate this issue, their performance remains limited, particularly in the class-incremental scenario which is considered natural and highly challenging. In this paper, we present a novel algorithm, called adaptive-experience replay (AdaER), to address the challenge of continual lifelong learning. AdaER consists of two stages: memory replay and memory update. In the memory replay stage, AdaER introduces a contextually-cued memory recall (C-CMR) strategy, which selectively replays memories that are most conflicting with the current input data in terms of both data and task. Additionally, AdaER incorporates an entropy-balanced reservoir sampling (E-BRS) strategy to enhance the performance of the memory buffer by maximizing information entropy. To evaluate the effectiveness of AdaER, we conduct experiments on established supervised continual lifelong learning benchmarks, specifically focusing on class-incremental learning scenarios. The results demonstrate that AdaER outperforms existing continual lifelong learning baselines, highlighting its efficacy in mitigating catastrophic forgetting and improving learning performance.

cs.LG↗

arXiv2023

Boosting Multi-modal Model Performance with Adaptive Gradient Modulation

While the field of multi-modal learning keeps growing fast, the deficiency of the standard joint training paradigm has become clear through recent studies. They attribute the sub-optimal performance of the jointly trained model to the modality competition phenomenon. Existing works attempt to improve the jointly trained model by modulating the training process. Despite their effectiveness, those methods can only apply to late fusion models. More importantly, the mechanism of the modality competition remains unexplored. In this paper, we first propose an adaptive gradient modulation method that can boost the performance of multi-modal models with various fusion strategies. Extensive experiments show that our method surpasses all existing modulation methods. Furthermore, to have a quantitative understanding of the modality competition and the mechanism behind the effectiveness of our modulation method, we introduce a novel metric to measure the competition strength. This metric is built on the mono-modal concept, a function that is designed to represent the competition-less state of a modality. Through systematic investigation, our results confirm the intuition that the modulation encourages the model to rely on the more informative modality. In addition, we find that the jointly trained model typically has a preferred modality on which the competition is weaker than other modalities. However, this preferred modality need not dominate others. Our code will be available at https://github.com/lihong2303/AGM_ICCV2023.

cs.CV↗

arXiv2023

Euler--Chern Correspondence via Topological Superconductivity

The Fermi sea topology is characterized by the Euler characteristics $χ_F$. In this paper, we examine how $χ_F$ of the metallic state is inhereted by the topological invariant of the superconducting state. We establish a correspondence between the Euler characteristic and the Chern number $C$ of $p$-wave topological superconductors without time-reversal symmetry in two dimensions. By rewriting the pairing potential $Δ_{\bf k}=Δ_1-iΔ_2$ as a vector field ${\bf u}=(Δ_1,Δ_2)$, we found that $χ_F=C$ when ${\bf u}$ and fermion velocity ${\bf v}$ can be smoothly deformed to be parallel or antiparallel on each Fermi surface. We also discuss a similar correspondence between Euler characteristic and 3D winding number of time-reversal-invariant $p$-wave topological superconductors in three dimensions.

cond-mat.mes-hall↗

arXiv2023

Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondence

Cross-view geo-localization aims to estimate the location of a query ground image by matching it to a reference geo-tagged aerial images database. As an extremely challenging task, its difficulties root in the drastic view changes and different capturing time between two views. Despite these difficulties, recent works achieve outstanding progress on cross-view geo-localization benchmarks. However, existing methods still suffer from poor performance on the cross-area benchmarks, in which the training and testing data are captured from two different regions. We attribute this deficiency to the lack of ability to extract the spatial configuration of visual feature layouts and models' overfitting on low-level details from the training set. In this paper, we propose GeoDTR which explicitly disentangles geometric information from raw features and learns the spatial correlations among visual features from aerial and ground pairs with a novel geometric layout extractor module. This module generates a set of geometric layout descriptors, modulating the raw features and producing high-quality latent representations. In addition, we elaborate on two categories of data augmentations, (i) Layout simulation, which varies the spatial configuration while keeping the low-level details intact. (ii) Semantic augmentation, which alters the low-level details and encourages the model to capture spatial configurations. These augmentations help to improve the performance of the cross-view geo-localization models, especially on the cross-area benchmarks. Moreover, we propose a counterfactual-based learning process to benefit the geometric layout extractor in exploring spatial information. Extensive experiments show that GeoDTR not only achieves state-of-the-art results but also significantly boosts the performance on same-area and cross-area benchmarks.

cs.CV↗

arXiv2023

Inspire creativity with ORIBA: Transform Artists' Original Characters into Chatbots through Large Language Model

This research delves into the intersection of illustration art and artificial intelligence (AI), focusing on how illustrators engage with AI agents that embody their original characters (OCs). We introduce 'ORIBA', a customizable AI chatbot that enables illustrators to converse with their OCs. This approach allows artists to not only receive responses from their OCs but also to observe their inner monologues and behavior. Despite the existing tension between artists and AI, our study explores innovative collaboration methods that are inspiring to illustrators. By examining the impact of AI on the creative process and the boundaries of authorship, we aim to enhance human-AI interactions in creative fields, with potential applications extending beyond illustration to interactive storytelling and more.

cs.MM↗

arXiv2023

The hydrostatic limit of the Beris-Edwards system in dimension two

We study the scaled anisotropic co-rotational Beris-Edwards system modeling the hydrodynamic motion of nematic liquid crystals in dimension two. We prove the global well-posedness with small analytic data in a thin strip domain. Moreover, we justify the limit to a system involving the hydrostatic Navier-Stokes system with analytic data and prove the convergence.

math.AP↗