Searcharxiv⌕ Search

arXiv subjects

Yi Xie

Publications and source records attributed to Yi Xie.

At least 91 records · Page 5Linked to original sources
arXiv2024

Thermometry of Trapped Ions Based on Bichromatic Driving

Accurate thermometry of laser-cooled ions is crucial for the performance of the trapped-ions quantum computing platform. However, most existing methods face a computational exponential bottleneck. Recently, a thermometry method based on bichromatic driving was theoretically proposed by Ivan Vybornyi et al. to overcome this obstacle, which allows the computational complexity to remain constant with the increase of ion numbers. In this paper, we provide a detailed statistical analysis of this method and prove its robustness to several imperfect experimental conditions using Floquet theory. We then experimentally verify its good performance on a linear segmented surface-electrode ion trap platform for the first time. This method is proven to be effective from near the motional ground state to a few mean phonon numbers. Our theoretical analysis and experimental verification demonstrate that the scheme can accurately and efficiently measure the temperature in ion crystals.

quant-ph↗
arXiv2024

Gravitational lensing of massive particles by a black-bounce-Schwarzschild black hole

We investigate in detail the weak-field gravitational lensing of a relativistic neutral massive particle induced by a regular black-bounce-Schwarzschild black hole proposed by Simpson and Visser. Starting with the calculation of the gravitational deflection of the massive particle up to the third post-Minkowskian order, the Virbhadra-Ellis lens equation is solved perturbatively beyond the weak-deflection limit to achieve the expressions for the lensing observables of the primary and secondary images of a point-like particle source. The main observables contain not only the positions, the flux magnifications, and the gravitational time delays of the individual images, but also the positional relations, the magnification relations (including the total magnification), the magnification centroid, and the differential time delay. We then discuss the velocity-induced effects originated from the deviation of the particle's initial velocity from the speed of light on the black-bounce-Schwarzschild lensing observables of the images of a point-like light source, and the effects induced by the bounce parameter of the spacetime on the measurable image properties of Schwarzschild lensing of the massive particle. As an application of the results, we model the supermassive black hole in the Galactic Center (i.e., Sgr A$^{\ast}$) as the lens, and focus on evaluating the possibilities to detect the new velocity-induced and bounce-induced effects on the practical lensing observables and analyzing the dependence of these effects on the parameters.

gr-qc↗
arXiv2024

Inference Performance Optimization for Large Language Models on CPUs

Large language models (LLMs) have shown exceptional performance and vast potential across diverse tasks. However, the deployment of LLMs with high performance in low-resource environments has garnered significant attention in the industry. When GPU hardware resources are limited, we can explore alternative options on CPUs. To mitigate the financial burden and alleviate constraints imposed by hardware resources, optimizing inference performance is necessary. In this paper, we introduce an easily deployable inference performance optimization solution aimed at accelerating LLMs on CPUs. In this solution, we implement an effective way to reduce the KV cache size while ensuring precision. We propose a distributed inference optimization approach and implement it based on oneAPI Collective Communications Library. Furthermore, we propose optimization approaches for LLMs on CPU, and conduct tailored optimizations for the most commonly used models. The code is open-sourced at https://github.com/intel/xFasterTransformer.

cs.AI↗
arXiv2024

ZBanner: Fast Stateless Scanning Capable of Obtaining Responses over TCP

Fast large-scale network scanning is an important way to understand internet service configurations and security in real time, among which stateless scan is representative. Existing stateless scanners can perform single-packet scans for internet-wide network measurements but are limited to host discovery or port scanning. To obtain further information over TCP, slower stateful scanners must be used in conjunction which spend more time and memory because of connection state maintenance. Through simplifying TCP finite state machine, this paper proposes a novel stateless scanning model, which can establish TCP connections and obtain further responses in a completely stateless manner. Based on this model, we implement ZBanner, an improved modular stateless scanner that utilizes user-defined probes for identifying services and versions, fingerprinting TLS servers, etc. We present unique design of ZBanner and experimentally characterize its feasibility and performance. Experiments show that ZBanner performs better than current state-of-the-art solutions in terms of scan rate and memory usage. ZBanner achieves at least three times faster than current tools for generic ports and over 90 times faster for open ports while keeping a minimum and stable memory usage.

cs.NI↗
arXiv2024

AttacKG+:Boosting Attack Knowledge Graph Construction with Large Language Models

Attack knowledge graph construction seeks to convert textual cyber threat intelligence (CTI) reports into structured representations, portraying the evolutionary traces of cyber attacks. Even though previous research has proposed various methods to construct attack knowledge graphs, they generally suffer from limited generalization capability to diverse knowledge types as well as requirement of expertise in model design and tuning. Addressing these limitations, we seek to utilize Large Language Models (LLMs), which have achieved enormous success in a broad range of tasks given exceptional capabilities in both language understanding and zero-shot task fulfillment. Thus, we propose a fully automatic LLM-based framework to construct attack knowledge graphs named: AttacKG+. Our framework consists of four consecutive modules: rewriter, parser, identifier, and summarizer, each of which is implemented by instruction prompting and in-context learning empowered by LLMs. Furthermore, we upgrade the existing attack knowledge schema and propose a comprehensive version. We represent a cyber attack as a temporally unfolding event, each temporal step of which encapsulates three layers of representation, including behavior graph, MITRE TTP labels, and state summary. Extensive evaluation demonstrates that: 1) our formulation seamlessly satisfies the information needs in threat event analysis, 2) our construction framework is effective in faithfully and accurately extracting the information defined by AttacKG+, and 3) our attack graph directly benefits downstream security practices such as attack reconstruction. All the code and datasets will be released upon acceptance.

cs.CR↗
arXiv2024

Entanglement signatures for quantum synchronization with single-ion phonon laser

The entanglement properties of quantum synchronization, based on a single-ion phonon laser subjected to an external drive, have been studied. It is found that the maximum value of steady-state entanglement between the ion's internal and external states occurs near the noiseless boundary from synchronization to unsynchronization, accompanied by noticeable oscillatory behaviors during the corresponding time evolution of entanglement. In addition, the later time dynamics of entanglement also indicates the occurrence of frequency entrainment, as evidenced by the strong consistency between the bending of the observed frequency and the emergence of Liouvillian exceptional points (LEPs) in the first two eigenvalues of the Liouvillian eigenspectrum. Moreover, the emergence of LEPs, which is intimately associated with frequency entrainment, should be widely observed in quantum synchronization and can be explored in LEPs-based applications.

quant-ph↗
arXiv2024

Mode-resolved thermometry of trapped ion with Deep Learning

In trapped ion system, accurate thermometry of ion is crucial for evaluating the system state and precisely performing quantum operations. However, when the motional state of a single ion is far away from the ground state, the spatial dimension of the phonon state sharply increases, making it difficult to realize accurate and mode-resolved thermometry with existing methods. In this work, we apply deep learning for the first time to the thermometry of trapped ion, providing an efficient and mode-resolved method for accurately estimating large mean phonon numbers. Our trained neural network model can be directly applied to other experimental setups without retraining or post-processing, as long as the related parameters are covered by the model's effective range, and it can also be conveniently extended to other parameter ranges. We have conducted experimental verification based on our surface trap, of which the result has shown the accuracy and efficiency of the method for thermometry of single ion under large mean phonon number, and its mode resolution characteristic can make it better applied to the characterization of system parameters, such as evaluating cooling effectiveness, analyzing surface trap noise.

quant-ph↗
arXiv2024

Characterizing the spatial potential of a surface electrode ion trap

The accurate characterization of the spatial potential generated by a planar electrode in a surface-type Paul trap is of great interest. To achieve this, we employ a simple yet highly precise parametric expression to describe the spatial field of a rectangular-shaped electrode. Based on this, an optimization method is introduced to precisely characterize the axial electric field intensity created by the powered electrode and the stray field. In contrast to existing methods, various types of experimental data, such as the equilibrium position of ions in a linear string, equilibrium positions of single trapped ions and trap frequencies, are utilized for potential estimation in order to mitigate systematic errors. This approach offers significant flexibility in voltage settings for data collection, making it particularly well-suited for surface electrode traps where ion probe trapping height may vary with casual voltage settings. In our demonstration, we successfully minimized the discrepancy between experimental observations and model predictions to an impressive extent. The relative errors of secular frequencies were suppressed within $\pm$ 0.5$\%$, and the positional error of ions was limited to less than 1.2 $μ$m, all surpassing those achieved by existing methodologies.

quant-ph↗
arXiv2024

Beimingwu: A Learnware Dock System

The learnware paradigm proposed by Zhou [2016] aims to enable users to reuse numerous existing well-trained models instead of building machine learning models from scratch, with the hope of solving new user tasks even beyond models' original purposes. In this paradigm, developers worldwide can submit their high-performing models spontaneously to the learnware dock system (formerly known as learnware market) without revealing their training data. Once the dock system accepts the model, it assigns a specification and accommodates the model. This specification allows the model to be adequately identified and assembled to reuse according to future users' needs, even if they have no prior knowledge of the model. This paradigm greatly differs from the current big model direction and it is expected that a learnware dock system housing millions or more high-performing models could offer excellent capabilities for both planned tasks where big models are applicable; and unplanned, specialized, data-sensitive scenarios where big models are not present or applicable. This paper describes Beimingwu, the first open-source learnware dock system providing foundational support for future research of learnware paradigm.The system significantly streamlines the model development for new user tasks, thanks to its integrated architecture and engine design, extensive engineering implementations and optimizations, and the integration of various algorithms for learnware identification and reuse. Notably, this is possible even for users with limited data and minimal expertise in machine learning, without compromising the raw data's security. Beimingwu supports the entire process of learnware paradigm. The system lays the foundation for future research in learnware-related algorithms and systems, and prepares the ground for hosting a vast array of learnwares and establishing a learnware ecosystem.

cs.SE↗
arXiv2024

SAME: Sample Reconstruction against Model Extraction Attacks

While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure. As a solution, Machine Learning as a Service (MLaaS) has emerged, lowering the barriers for users to release or productize their deep learning models. However, previous studies have highlighted potential privacy and security concerns associated with MLaaS, and one primary threat is model extraction attacks. To address this, there are many defense solutions but they suffer from unrealistic assumptions and generalization issues, making them less practical for reliable protection. Driven by these limitations, we introduce a novel defense mechanism, SAME, based on the concept of sample reconstruction. This strategy imposes minimal prerequisites on the defender's capabilities, eliminating the need for auxiliary Out-of-Distribution (OOD) datasets, user query history, white-box model access, and additional intervention during model training. It is compatible with existing active defense methods. Our extensive experiments corroborate the superior efficacy of SAME over state-of-the-art solutions. Our code is available at https://github.com/xythink/SAME.

cs.CR↗
arXiv2023

Evidence of Dark Contents in the Center of NGC 6517

Millisecond pulsars can serve as effective probes to investigate the presence of Intermediate-mass Black Holes (IMBHs) within Galactic globular clusters (GCs). Based on the standard structure models for GCs, we conduct simulations to analyze the distributions of pulsar accelerations within the central region of NGC 6517. By comparing the measured accelerations of pulsars obtained from their period derivatives $\dot P$ to the simulated distribution profiles, we demonstrate that a central excess of dark mass is required to account for the measured accelerations. Our analysis, which relies on existing pulsar timing observations, is currently unable to differentiate between two possible scenarios: an IMBH precisely situated at the core of the cluster with mass $\gtrsim 9000^{+4000}_{-3000}~M_{\odot}$, or a central concentration of stellar mass dark remnants with a comparable total mass. However, with additional acceleration measurements from a few more pulsars in the cluster, it will be possible to differentiate the source of the nonluminous matter.

astro-ph.HE↗
arXiv2023

Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review

With the rapid development of artificial intelligence, large language models (LLMs) have shown promising capabilities in mimicking human-level language comprehension and reasoning. This has sparked significant interest in applying LLMs to enhance various aspects of healthcare, ranging from medical education to clinical decision support. However, medicine involves multifaceted data modalities and nuanced reasoning skills, presenting challenges for integrating LLMs. This paper provides a comprehensive review on the applications and implications of LLMs in medicine. It begins by examining the fundamental applications of general-purpose and specialized LLMs, demonstrating their utilities in knowledge retrieval, research support, clinical workflow automation, and diagnostic assistance. Recognizing the inherent multimodality of medicine, the review then focuses on multimodal LLMs, investigating their ability to process diverse data types like medical imaging and EHRs to augment diagnostic accuracy. To address LLMs' limitations regarding personalization and complex clinical reasoning, the paper explores the emerging development of LLM-powered autonomous agents for healthcare. Furthermore, it summarizes the evaluation methodologies for assessing LLMs' reliability and safety in medical contexts. Overall, this review offers an extensive analysis on the transformative potential of LLMs in modern medicine. It also highlights the pivotal need for continuous optimizations and ethical oversight before these models can be effectively integrated into clinical practice. Visit https://github.com/mingze-yuan/Awesome-LLM-Healthcare for an accompanying GitHub repository containing latest papers.

cs.CL↗
arXiv2023

Configuration space integrals and formal smooth structures

Watanabe disproved the 4-dimensional Smale conjecture by constructing topologically trivial $D^{4}$-bundles over spheres and showing that they are smoothly nontrivial using configuration space integrals. In this paper, we define a new version of configuration space integrals that only relies on a formal smooth structure on the $D^{4}$-bundle (i.e., a vector bundle structure on the vertical tangent microbundle). It coincides with Watanabe's definition when the $D^{4}$-bundle is smooth. We obtain several applications. First, we give a lower bound (in terms of the graph homology) on the dimension of the rational homotopy and homology groups of $\textrm{Top}(4)$ and $\textrm{Homeo}(S^4)$ (the homeomorphism group of $\mathbb{R}^4$ and $S^4$). In particular, this implies that $\textrm{Top}(4)$ and $\textrm{Homeo}(S^4)$ are not rationally equivalent to any finite-dimensional CW complexes. Second, we discover a generalized Miller-Morita-Mumford class $κ_θ(π)\in H^{3}(B;\mathbf{Q})$, which is defined for any topological 4-manifold bundle $X\to E\to B$. This class obstructs the existence of a formal smooth structure on the bundle. Third, we show that for any compact, orientable, smooth 4-manifold $X$ (possibly with boundary), the inclusion map from its diffeomorphism group to its homeomorphism group is not rationally $2$-connected (hence not a weak homotopy equivalence). This implies that the space of smooth structures on $X$ has a nontrivial rational homotopy group in dimension 2.

math.GT↗
arXiv2023

Ring structures in singular instanton homology

We calculate the ring structure of the singular instanton Floer homology of $(S^1\times Σ, S^1\times \{p_1,\dots,p_n\})$ with C-coefficients, where $Σ$ is a closed oriented surface. As an application, we prove an excision formula for singular instanton homology when n=1. This settles the last unknown case of excision formula for instanton Floer homology.

math.GT↗
arXiv2023

Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval

Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective knowledge imitation during the most critical early training period, causing final performance degeneration. To tackle this issue, we propose a Capacity Dynamic Distillation framework, which constructs a student model with editable representation capacity. Specifically, the employed student model is initially a heavy model to fruitfully learn distilled knowledge in the early training epochs, and the student model is gradually compressed during the training. To dynamically adjust the model capacity, our dynamic framework inserts a learnable convolutional layer within each residual block in the student model as the channel importance indicator. The indicator is optimized simultaneously by the image retrieval loss and the compression loss, and a retrieval-guided gradient resetting mechanism is proposed to release the gradient conflict. Extensive experiments show that our method has superior inference speed and accuracy, e.g., on the VeRi-776 dataset, given the ResNet101 as a teacher, our method saves 67.13% model parameters and 65.67% FLOPs (around 24.13% and 21.94% higher than state-of-the-arts) without sacrificing accuracy (around 2.11% mAP higher than state-of-the-arts).

cs.CV↗
arXiv2023

Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers

Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures emit tokens at each frame, relying only on current and past signal, while non-causal models are exposed to a window of future frames at each step to increase predictive accuracy. This dichotomy amounts to a trade-off for real-time Automatic Speech Recognition (ASR) system design: profit from the low-latency benefit of strictly-causal architectures while accepting predictive performance limitations, or realize the modeling benefits of future-context models accompanied by their higher latency penalty. In this work, we relax the constraints of this choice and present the Adaptive Non-Causal Attention Transducer (ANCAT). Our architecture is non-causal in the traditional sense, but executes in a low-latency, streaming manner by dynamically choosing when to rely on future context and to what degree within the audio stream. The resulting mechanism, when coupled with our novel regularization algorithms, delivers comparable accuracy to non-causal configurations while improving significantly upon latency, closing the gap with their causal counterparts. We showcase our design experimentally by reporting comparative ASR task results with measures of accuracy and latency on both publicly accessible and production-scale, voice-assistant datasets.

eess.AS↗
arXiv2023

A deformation of Asaeda-Przytycki-Sikora homology

We define a 1-parameter family of homology invariants for links in thickened oriented surfaces. It recovers the homology invariant of Asaeda-Przytycki-Sikora (arxiv:0409414) and the invariant defined by Winkeler (arxiv:2106.03834). The new invariant can be regarded as a deformation of Asaeda-Przytycki-Sikora homology; it is not a Lee-type deformation as the deformation is only non-trivial when the surface is not simply connected. Our construction is motivated by computations in singular instanton Floer homology. We also prove a detection property for the new invariant, which is a stronger result than the main theorem of arxiv:2208.13963.

math.GT↗
arXiv2023

GiT: Graph Interactive Transformer for Vehicle Re-identification

Transformers are more and more popular in computer vision, which treat an image as a sequence of patches and learn robust global features from the sequence. However, pure transformers are not entirely suitable for vehicle re-identification because vehicle re-identification requires both robust global features and discriminative local features. For that, a graph interactive transformer (GiT) is proposed in this paper. In the macro view, a list of GiT blocks are stacked to build a vehicle re-identification model, in where graphs are to extract discriminative local features within patches and transformers are to extract robust global features among patches. In the micro view, graphs and transformers are in an interactive status, bringing effective cooperation between local and global features. Specifically, one current graph is embedded after the former level's graph and transformer, while the current transform is embedded after the current graph and the former level's transformer. In addition to the interaction between graphs and transforms, the graph is a newly-designed local correction graph, which learns discriminative local features within a patch by exploring nodes' relationships. Extensive experiments on three large-scale vehicle re-identification datasets demonstrate that our GiT method is superior to state-of-the-art vehicle re-identification approaches.

cs.CV↗