Search

Recent research has made significant progress in understanding localization transitions and mobility edges (MEs) that separate extended and localized states in non-Hermitian (NH) quasicrystals. Here we focus on studying critical states and anomalous MEs, which identify the boundaries between critical and localized states within two distinct NH quasiperiodic models. Specifically, the first model is a quasiperiodic mosaic lattice with both nonreciprocal hopping term and on-site potential. In contrast, the second model features an unbounded quasiperiodic on-site potential and nonreciprocal hopping. Using Avila's global theory, we analytically derive the Lyapunov exponent and exact anomalous MEs. To confirm the emergence of the robust critical states in both models, we conduct a numerical multifractal analysis of the wave functions and spectrum analysis of level spacing. Furthermore, we investigate the transition between real and complex spectra and the topological origins of the anomalous MEs. Our results may shed light on exploring the critical states and anomalous MEs in NH quasiperiodic systems.

Vision-language pretraining (VLP) with transformers has demonstrated exceptional performance across numerous multimodal tasks. However, the adversarial robustness of these models has not been thoroughly investigated. Existing multimodal attack methods have largely overlooked cross-modal interactions between visual and textual modalities, particularly in the context of cross-attention mechanisms. In this paper, we study the adversarial vulnerability of recent VLP transformers and design a novel Joint Multimodal Transformer Feature Attack (JMTFA) that concurrently introduces adversarial perturbations in both visual and textual modalities under white-box settings. JMTFA strategically targets attention relevance scores to disrupt important features within each modality, generating adversarial samples by fusing perturbations and leading to erroneous model predictions. Experimental results indicate that the proposed approach achieves high attack success rates on vision-language understanding and reasoning downstream tasks compared to existing baselines. Notably, our findings reveal that the textual modality significantly influences the complex fusion processes within VLP transformers. Moreover, we observe no apparent relationship between model size and adversarial robustness under our proposed attacks. These insights emphasize a new dimension of adversarial robustness and underscore potential risks in the reliable deployment of multimodal AI systems.

The mobility edge (ME) is a fundamental concept in the Anderson localized systems, which marks the energy separating extended and localized states. Although the ME and localization phenomena have been extensively studied in non-Hermitian (NH) quasiperiodic tight-binding models, they remain limited to NH continuum systems. Here, we investigate the ME and localization properties of a one-dimensional (1D) NH quasiperiodic continuous system, which is described by a Schr{\"o}dinger equation with an imaginary vector potential and an incommensurable one-site potential. We find that the ME is located in the real spectrum and falls between the localized and extended states. Additionally, we show that under the periodic boundary condition, the energy spectrum always exhibits an open curve representing high-energy extended electronic states characterized by a non-zero integer winding number. This complex spectrum topology is closely connected with the non-Hermitian skin effect (NHSE) observed under open boundary conditions, where the eigenstates of the bulk bands accumulate at the boundaries. Furthermore, we analyze the critical behavior of the localization transition and obtain critical potential amplitude accompanied by the universal critical exponent $\nu \simeq 1/3$. Our study provides valuable inspiration for exploring MEs and localization behaviors in NH quasiperiodic continuous systems.

Recent research has observed the occurrence of pseudo-mobility edge (ME) within a modulated mosaic model incorporating the Wannier-Stark potential. This pseudo-ME, which signifies the critical energy that distinguishes between ergodic and weakly ergodic, or weakly ergodic and nonergodic states, is a crucial concept in comprehending the transport and localization phenomena in Wannier-Stark systems. Here we investigate the influence of dissipation on a finite-height mosaic Wannier-Stark lattice that features such pseudo-MEs by computing the steady state density matrix. Our findings indicate that particular dissipation can steer the system into specific states, regardless of its initial state, predominantly characterized by either ergodic or nonergodic states. This suggests that dissipation can be harnessed as a novel method for inducing transitions between these states and manipulating particle localization behaviors in disorder-free systems., Comment: 9 pages, 5 figures, comments are welcome

Meticulous 3D environment representations have been a longstanding goal in computer vision and robotics fields. The recent emergence of neural implicit representations has introduced radical innovation to this field as implicit representations enable numerous capabilities. Among these, the Neural Radiance Field (NeRF) has sparked a trend because of the huge representational advantages, such as simplified mathematical models, compact environment storage, and continuous scene representations. Apart from computer vision, NeRF has also shown tremendous potential in the field of robotics. Thus, we create this survey to provide a comprehensive understanding of NeRF in the field of robotics. By exploring the advantages and limitations of NeRF, as well as its current applications and future potential, we hope to shed light on this promising area of research. Our survey is divided into two main sections: \textit{The Application of NeRF in Robotics} and \textit{The Advance of NeRF in Robotics}, from the perspective of how NeRF enters the field of robotics. In the first section, we introduce and analyze some works that have been or could be used in the field of robotics from the perception and interaction perspectives. In the second section, we show some works related to improving NeRF's own properties, which are essential for deploying NeRF in the field of robotics. In the discussion section of the review, we summarize the existing challenges and provide some valuable future research directions for reference., Comment: 21 pages, 19 figures

Quantum Federated Learning (QFL) is an emerging concept that aims to unfold federated learning (FL) over quantum networks, enabling collaborative quantum model training along with local data privacy. We explore the challenges of deploying QFL on cloud platforms, emphasizing quantum intricacies and platform limitations. The proposed data-encoding-driven QFL, with a proof of concept (GitHub Open Source) using genomic data sets on quantum simulators, shows promising results., Comment: SIGCOMM 2024, Quantum Computing, Federated Learning, Qiskit

Unsupervised Text Style Transfer (UTST) has emerged as a critical task within the domain of Natural Language Processing (NLP), aiming to transfer one stylistic aspect of a sentence into another style without changing its semantics, syntax, or other attributes. This task is especially challenging given the intrinsic lack of parallel text pairings. Among existing methods for UTST tasks, attention masking approach and Large Language Models (LLMs) are deemed as two pioneering methods. However, they have shortcomings in generating unsmooth sentences and changing the original contents, respectively. In this paper, we investigate if we can combine these two methods effectively. We propose four ways of interactions, that are pipeline framework with tuned orders; knowledge distillation from LLMs to attention masking model; in-context learning with constructed parallel examples. We empirically show these multi-way interactions can improve the baselines in certain perspective of style strength, content preservation and text fluency. Experiments also demonstrate that simply conducting prompting followed by attention masking-based revision can consistently surpass the other systems, including supervised text style transfer systems. On Yelp-clean and Amazon-clean datasets, it improves the previously best mean metric by 0.5 and 3.0 absolute percentages respectively, and achieves new SOTA results.

Non-Hermitian skin effect (NHSE), namely that eigenstates of non-Hermitian Hamiltonains are localized at one boundary in the open boundary condition, attracts great interest recently.In this paper, we investigate the skin effect in one-dimensional dissipative quantum many-body systems, which we call the Liouvillian skin effect (LSE). We rigorously identify the existence of LSE for generalized boundary conditions by solving the Liouvillian superoperator of an exactly solvable model with the advantage of Bethe ansatz. The LSE is sensitive to boundary conditions where the signature is reflected in eigenfunctions of the system. We confirm that the LSE is fragile to a tiny co-flow boundary hopping with non-Hermitian current but can survive for a counter-flow boundary hopping in the thermodynamic limit. Our work provides a prototypical example of exactly solvable dissipative quantum many-body lattice systems exhibiting LSE for generalized boundary conditions. It can be further extended to other integrable open quantum many-body models., Comment: 15 pages, 5 figures. Comments are welcome

Sketch-based terrain generation seeks to create realistic landscapes for virtual environments in various applications such as computer games, animation and virtual reality. Recently, deep learning based terrain generation has emerged, notably the ones based on generative adversarial networks (GAN). However, these methods often struggle to fulfill the requirements of flexible user control and maintain generative diversity for realistic terrain. Therefore, we propose a novel diffusion-based method, namely terrain diffusion network (TDN), which actively incorporates user guidance for enhanced controllability, taking into account terrain features like rivers, ridges, basins, and peaks. Instead of adhering to a conventional monolithic denoising process, which often compromises the fidelity of terrain details or the alignment with user control, a multi-level denoising scheme is proposed to generate more realistic terrains by taking into account fine-grained details, particularly those related to climatic patterns influenced by erosion and tectonic activities. Specifically, three terrain synthesisers are designed for structural, intermediate, and fine-grained level denoising purposes, which allow each synthesiser concentrate on a distinct terrain aspect. Moreover, to maximise the efficiency of our TDN, we further introduce terrain and sketch latent spaces for the synthesizers with pre-trained terrain autoencoders. Comprehensive experiments on a new dataset constructed from NASA Topology Images clearly demonstrate the effectiveness of our proposed method, achieving the state-of-the-art performance. Our code and dataset will be publicly available.

Recommending items to potentially interested users has been an important commercial task that faces two main challenges: accuracy and explainability. While most collaborative filtering models rely on statistical computations on a large scale of interaction data between users and items and can achieve high performance, they often lack clear explanatory power. We propose UIPC-MF, a prototype-based matrix factorization method for explainable collaborative filtering recommendations. In UIPC-MF, both users and items are associated with sets of prototypes, capturing general collaborative attributes. To enhance explainability, UIPC-MF learns connection weights that reflect the associative relations between user and item prototypes for recommendations. UIPC-MF outperforms other prototype-based baseline methods in terms of Hit Ratio and Normalized Discounted Cumulative Gain on three datasets, while also providing better transparency.

Similar vulnerability repeats in real-world software products because of code reuse, especially in wildly reused third-party code and libraries. Detecting repeating vulnerabilities like 1-day and N-day vulnerabilities is an important cyber security task. Unfortunately, the state-of-the-art methods suffer from poor performance because they detect patch existence instead of vulnerability existence and infer the vulnerability signature directly from binary code. In this paper, we propose VulMatch to extract precise vulnerability-related binary instructions to generate the vulnerability-related signature. VulMatch detects vulnerability existence based on binary signatures. Unlike previous approaches, VulMatch accurately locates vulnerability-related instructions by utilizing source and binary codes. Our experiments were conducted using over 1000 vulnerable instances across seven open-source projects. VulMatch significantly outperformed the baseline tools Asm2vec and Palmtree. Besides the performance advantages over the baseline tools, VulMatch offers a better feature by providing explainable reasons during vulnerability detection. Our empirical studies demonstrate that VulMatch detects fine-grained vulnerability that the state-of-the-art tools struggle with. Our experiment on commercial firmware demonstrates VulMatch is able to find vulnerabilities in real-world scenario., Comment: 15 pages IEEE journal template

Most existing 3D instance segmentation methods are derived from 3D semantic segmentation models. However, these indirect approaches suffer from certain limitations. They fail to fully leverage global and local semantic information for accurate prediction, which hampers the overall performance of the 3D instance segmentation framework. To address these issues, this paper presents PSGformer, a novel 3D instance segmentation network. PSGformer incorporates two key advancements to enhance the performance of 3D instance segmentation. Firstly, we propose a Multi-Level Semantic Aggregation Module, which effectively captures scene features by employing foreground point filtering and multi-radius aggregation. This module enables the acquisition of more detailed semantic information from global and local perspectives. Secondly, PSGformer introduces a Parallel Feature Fusion Transformer Module that independently processes super-point features and aggregated features using transformers. The model achieves a more comprehensive feature representation by the features which connect global and local features. We conducted extensive experiments on the ScanNetv2 dataset. Notably, PSGformer exceeds compared state-of-the-art methods by 2.2% on ScanNetv2 hidden test set in terms of mAP. Our code and models will be publicly released.

There are increasing concerns about malicious attacks on autonomous vehicles. In particular, inaudible voice command attacks pose a significant threat as voice commands become available in autonomous driving systems. How to empirically defend against these inaudible attacks remains an open question. Previous research investigates utilizing deep learning-based multimodal fusion for defense, without considering the model uncertainty in trustworthiness. As deep learning has been applied to increasingly sensitive tasks, uncertainty measurement is crucial in helping improve model robustness, especially in mission-critical scenarios. In this paper, we propose the Multimodal Fusion Framework (MFF) as an intelligent security system to defend against inaudible voice command attacks. MFF fuses heterogeneous audio-vision modalities using VGG family neural networks and achieves the detection accuracy of 92.25% in the comparative fusion method empirical study. Additionally, extensive experiments on audio-vision tasks reveal the model's uncertainty. Using Expected Calibration Errors, we measure calibration errors and Monte-Carlo Dropout to estimate the predictive distribution for the proposed models. Our findings show empirically to train robust multimodal models, improve standard accuracy and provide a further step toward interpretability. Finally, we discuss the pros and cons of our approach and its applicability for Advanced Driver Assistance Systems.

The close integration of increasing operating units into an integrated energy system (IES) results in complex interconnections between these units. The strong dynamic interactions create barriers to designing a successful distributed coordinated controller to achieve synergy between all the units and unlock the potential for grid response. To address these challenges, we introduce a directed graph representation of IESs using an augmented Jacobian matrix to depict their underlying dynamics topology. By utilizing this representation, a generic subsystem decomposition method is proposed to partition the entire IES vertically based on the dynamic time scale and horizontally based on the closeness of interconnections between the operating units. Exploiting the decomposed subsystems, we develop a cooperative distributed economic model predictive control (DEMPC) with multiple global objectives that regulate the generated power at the grid's requests and satisfy the customers cooling and system economic requirements. In the DEMPC, multiple local decision-making agents cooperate sequentially and iteratively to leverage the potential across all the units for system-wide dynamic synergy. Furthermore, we discuss how subsystem decomposition impacts the design of distributed cooperation schemes for IESs and provide a control-oriented basic guideline on the optimal decomposition of complex energy systems. Extensive simulations demonstrate that the control strategies with different levels of decomposition and collaboration will lead to marked differences in the overall performance of IES. The standard control scheme based on the proposed subsystem configuration outperforms the empirical decomposition-based control benchmark by about 20%. The DEMPC architecture further improves the overall performance of the IES by about 55% compared to the benchmark.

Voice assistant applications have become omniscient nowadays. Two models that provide the two most important functions for real-life applications (i.e., Google Home, Amazon Alexa, Siri, etc.) are Automatic Speech Recognition (ASR) models and Speaker Identification (SI) models. According to recent studies, security and privacy threats have also emerged with the rapid development of the Internet of Things (IoT). The security issues researched include attack techniques toward machine learning models and other hardware components widely used in voice assistant applications. The privacy issues include technical-wise information stealing and policy-wise privacy breaches. The voice assistant application takes a steadily growing market share every year, but their privacy and security issues never stopped causing huge economic losses and endangering users' personal sensitive information. Thus, it is important to have a comprehensive survey to outline the categorization of the current research regarding the security and privacy problems of voice assistant applications. This paper concludes and assesses five kinds of security attacks and three types of privacy threats in the papers published in the top-tier conferences of cyber security and voice domain., Comment: 5 figures

Passive radiative cooling technologies are highly attractive in pursuing sustainable development. However, current cooling materials are often static, which makes it difficult to cope with the varying needs of all-weather thermal comfort management. Herein, a strategy is designed to obtain flexible thermoplastic polyurethane nanofiber (Es-TPU) membranes via electrospinning, realizing reversible in-situ solvent-free switching between radiative cooling and solar heating through changes in its optical reflectivity by stretching. In its radiative cooling state (0% strain), the Es-TPU membrane shows a high and angular-independent reflectance of 95.6% in the 0.25-2.5 {\mu}m wavelength range and an infrared emissivity of 93.3% in the atmospheric transparency window (8-13 {\mu}m), reaching a temperature drop of 10 {\deg}C at midday, with a corresponding cooling power of 118.25 W/m2. The excellent mechanical properties of the Es-TPU membrane allows the continuous adjustment of reflectivity by reversibly stretching it, reaching a reflectivity of 61.1% ({\Delta}R=34.5%) under an elongation strain of 80%, leading to a net temperature increase of 9.5 {\deg}C above ambient of an absorbing substrate and an equivalent power of 220.34 W/m2 in this solar heating mode. The strong haze, hydrophobicity and outstanding aging resistance exhibited by this scalable membrane hold promise for achieving uniform illumination with tunable strength and efficient thermal management in practical applications., Comment: accepted version of the manuscript published on Chemical Engineering Journal

Nanostructured topological insulators (TIs) have the potential to impact a wide array of condensed matter physics topics, ranging from Majorana physics to spintronics. However, the most common TI materials, the Bi$_2$Se$_3$ family, are easily damaged during nanofabrication of devices. In this paper, we show that electron beam lithography performed with a 30 or 50 kV accelerating voltage -- common for nanopatterning in academic facilities -- damages both nonmagnetic TIs and their magnetically-doped counterparts at unacceptable levels. We additionally demonstrate that electron beam lithography with a 10 kV accelerating voltage produces minimal damage detectable through low-temperature electronic transport. Although reduced accelerating voltages present challenges in creating fine features, we show that with careful choice of processing parameters, particularly the resist, 100 nm features are reliably achievable., Comment: 10 pages, 5 figures