arXiv subjects

Ying Wang

Publications and source records attributed to Ying Wang.

At least 217 records · Page 12Linked to original sources

arXiv2024

Qsco: A Quantum Scoring Module for Open-set Supervised Anomaly Detection

Open set anomaly detection (OSAD) is a crucial task that aims to identify abnormal patterns or behaviors in data sets, especially when the anomalies observed during training do not represent all possible classes of anomalies. The recent advances in quantum computing in handling complex data structures and improving machine learning models herald a paradigm shift in anomaly detection methodologies. This study proposes a Quantum Scoring Module (Qsco), embedding quantum variational circuits into neural networks to enhance the model's processing capabilities in handling uncertainty and unlabeled data. Extensive experiments conducted across eight real-world anomaly detection datasets demonstrate our model's superior performance in detecting anomalies across varied settings and reveal that integrating quantum simulators does not result in prohibitive time complexities. Our study validates the feasibility of quantum-enhanced anomaly detection methods in practical applications.

cs.LG↗

arXiv2024

Efficient Scaling of Diffusion Transformers for Text-to-Image Generation

We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training scaled DiTs ranging from 0.3B upto 8B parameters on datasets up to 600M images. We find that U-ViT, a pure self-attention based DiT model provides a simpler design and scales more effectively in comparison with cross-attention based DiT variants, which allows straightforward expansion for extra conditions and other modalities. We identify a 2.3B U-ViT model can get better performance than SDXL UNet and other DiT variants in controlled setting. On the data scaling side, we investigate how increasing dataset size and enhanced long caption improve the text-image alignment performance and the learning efficiency.

cs.CV↗

arXiv2024

BodyMetric: Evaluating the Realism of Human Bodies in Text-to-Image Generation

Accurately generating images of human bodies from text remains a challenging problem for state of the art text-to-image models. Commonly observed body-related artifacts include extra or missing limbs, unrealistic poses, blurred body parts, etc. Currently, evaluation of such artifacts relies heavily on time-consuming human judgments, limiting the ability to benchmark models at scale. We address this by proposing BodyMetric, a learnable metric that predicts body realism in images. BodyMetric is trained on realism labels and multi-modal signals including 3D body representations inferred from the input image, and textual descriptions. In order to facilitate this approach, we design an annotation pipeline to collect expert ratings on human body realism leading to a new dataset for this task, namely, BodyRealism. Ablation studies support our architectural choices for BodyMetric and the importance of leveraging a 3D human body prior in capturing body-related artifacts in 2D images. In comparison to concurrent metrics which evaluate general user preference in images, BodyMetric specifically reflects body-related artifacts. We demonstrate the utility of BodyMetric through applications that were previously infeasible at scale. In particular, we use BodyMetric to benchmark the generation ability of text-to-image models to produce realistic human bodies. We also demonstrate the effectiveness of BodyMetric in ranking generated images based on the predicted realism scores.

cs.CV↗

arXiv2024

Analog-Only Beamforming for Near-Field Multiuser MIMO Communications

For the existing near-field multiuser communications based on hybrid beamforming (HBF) architectures, high-quality effective channel estimation is required to obtain the channel state information (CSI) for the design of the digital beamformer. To simplify the system reconfiguration and eliminate the pilot overhead required by the effective channel estimation, we considered an analog-only beamforming (AoBF) architecture in this study. The AoBF is designed with the aim of maximizing the sum rate, which is then transformed into a problem, maximizing the power transmitted to the target user equipment (UE) and meanwhile minimizing the power leaked to the other UEs. To solve this problem, we used beam focusing and beam nulling and proposed two AoBF schemes based on the majorization-minimization (MM) algorithm. First, the AoBF scheme based on perfect CSI is proposed, with the focus on the beamforming performance and regardless of the CSI acquisition. Then, the AoBF scheme based on imperfect CSI is proposed, where the low-dimensional imperfect CSI is obtained by beam sweeping based on a near-field codebook. Simulation results demonstrate that the two AoBF schemes can approach the sum rate of the HBF schemes but outperform HBF schemes in terms of energy efficiency (EE).

cs.IT↗

arXiv2024

Recursive Projection-Free Identification with Binary-Valued Observations

This paper is concerned with parameter identification problem for finite impulse response (FIR) systems with binary-valued observations under low computational complexity. Most of the existing algorithms under binary-valued observations rely on projection operators, which leads to a high computational complexity of much higher than O(n^2). In response, this paper introduces a recursive projection-free identification algorithm that incorporates a specialized cut-off coefficient to fully utilize prior information, thereby eliminating the need for projection operators. The algorithm is proved to be mean square and almost surely convergent. Furthermore, to better leverage prior information, an adaptive accelerated coefficient is introduced, resulting in a mean square convergence rate of O(1/k) , which matches the convergence rate with accurate observations. Inspired by the structure of the Cramer-Rao lower bound, the algorithm can be extended to an information-matrix projection-free algorithm by designing adaptive weight coefficients. This extension is proved to be asymptotically efficient for first-order FIR systems, with simulations indicating similar results for high order FIR systems. Finally, numerical examples are provided to demonstrate the main results.

eess.SY↗

arXiv2024

Intertwining operators beyond the Stark Effect

The main mathematical manifestation of the Stark effect in quantum mechanics is the shift and the formation of clusters of eigenvalues when a spherical Hamiltonian is perturbed by lower order terms. Understanding this mechanism turned out to be fundamental in the description of the large-time asymptotics of the associated Schrödinger groups and can be responsible for the lack of dispersion in Fanelli, Felli, Fontelos and Primo [Comm. Math. Phys., 324(2013), 1033-1067; 337(2015), 1515-1533]. Recently, Miao, Su, and Zheng introduced in [Tran. Amer. Math. Soc., 376(2023), 1739--1797] a family of spectrally projected intertwining operators, reminiscent of the Kato's wave operators, in the case of constant perturbations on the sphere (inverse-square potential), and also proved their boundedness in $L^p$. Our aim is to establish a general framework in which some suitable intertwining operators can be defined also for non constant spherical perturbations in space dimensions 2 and higher. In addition, we investigate the mapping properties between $L^p$-spaces of these operators. In 2D, we prove a complete result, for the Schrödinger Hamiltonian with a (fixed) magnetic potential an electric potential, both scaling critical, allowing us to prove dispersive estimates, uniform resolvent estimates, and $L^p$-bounds of Bochner--Riesz means. In higher dimensions, apart from recovering the example of inverse-square potential, we can conjecture a complete result in presence of some symmetries (zonal potentials), and open some interesting spectral problems concerning the asymptotics of eigenfunctions.

math.AP↗

arXiv2024

Explicit symplectic integrators with adaptive time steps in curved spacetimes

Recently, our group developed explicit symplectic methods for curved spacetimes that are not split into several explicitly integrable parts, but are via appropriate time transformations. Such time-transformed explicit symplectic integrators should have employed adaptive time steps in principle, but they are often difficult in practical implementations. In fact, they work well if time transformation functions cause the time-transformed Hamiltonians to have the desired splits and approach 1 or constants for sufficiently large distances. However, they do not satisfy the requirement of step-size selections in this case. Based on the step-size control technique proposed by Preto $\&$ Saha, the nonadaptive time step time-transformed explicit symplectic methods are slightly adjusted as adaptive ones. The adaptive methods have only two additional steps and a negligible increase in computational cost as compared with the nonadaptive ones. Their implementation is simple. Several dynamical simulations of particles and photons near black holes have demonstrated that the adaptive methods typically improve the efficiency of the nonadaptive methods. Because of the desirable property, the new adaptive methods are applied to investigate the chaotic dynamics of particles and photons outside the horizon in a Schwarzschild-Melvin spacetime. The new methods are widely applicable to all curved spacetimes corresponding to Hamiltonians or time-transformed Hamiltonians with the expected splits. Also application to the backwards ray-tracing method for studying the motion of photons and shadows of black holes is possible.

gr-qc↗

arXiv2024

SNS Junctions along the BCS-BEC Crossover

We present a theory of SNS junctions, a normal metal sandwiched between two superconductors, along the crossover from the BCS to the BEC regime. We calculate the Josephson current as a function of the chemical potential relative to the band edge in the superconducting region, $μ_S$, where the BEC phase is indicated by $μ_S <0$. The chemical potential relative to the band edge in the normal metal, $μ_N$, allows us to tune the junction between the SNS case ($μ_N>0$) and the SIS case, where the superconductors are separated by a tunneling barrier. We find that there are Andreev levels in the BEC regime, as long as there is sufficient density of states in the normal region, i.e. when $μ_N>Δ$, where $Δ$ is the amplitude of the superconducting order parameter. For 1D SNS junctions, we find the Josephson current $I_S$ carried by these Andreev levels to be a function of the ratio $Δ/Δ_d$, where $Δ_d$ is the Andreev level spacing. At zero temperature, the Josephson current has a maximum on the BCS side of the transition where $Δ$ is maximal. At finite temperature, however, we find that the maximum moves to the BEC side of the crossover. We identify the mechanism for this phenomenon to be the decrease in the number of Andreev levels at the BCS-BEC crossover, accompanied by an increase in excitation energy to the unoccupied levels, making it less likely that these states are thermally occupied. Thereby, at finite temperature, the Josephson current is more strongly reduced on the BCS side of the crossover, resulting in a maximal Josephson current at the BCS-BEC crossover.

cond-mat.supr-con↗

arXiv2024

Dependency-Aware CAV Task Scheduling via Diffusion-Based Reinforcement Learning

In this paper, we propose a novel dependency-aware task scheduling strategy for dynamic unmanned aerial vehicle-assisted connected autonomous vehicles (CAVs). Specifically, different computation tasks of CAVs consisting of multiple dependency subtasks are judiciously assigned to nearby CAVs or the base station for promptly completing tasks. Therefore, we formulate a joint scheduling priority and subtask assignment optimization problem with the objective of minimizing the average task completion time. The problem aims at improving the long-term system performance, which is reformulated as a Markov decision process. To solve the problem, we further propose a diffusion-based reinforcement learning algorithm, named Synthetic DDQN based Subtasks Scheduling, which can make adaptive task scheduling decision in real time. A diffusion model-based synthetic experience replay is integrated into the reinforcement learning framework, which can generate sufficient synthetic data in experience replay buffer, thereby significantly accelerating convergence and improving sample efficiency. Simulation results demonstrate the effectiveness of the proposed algorithm on reducing task completion time, comparing to benchmark schemes.

cs.AI↗

arXiv2024

Fast High-Quality Enhanced Imaging Algorithm for Layered Dielectric Targets Based on MMW MIMO-SAR System

Millimeter-wave (MMW) multiple-input multiple-output synthetic aperture radar (MIMO-SAR) system is a technology that can achieve high resolution, high frame rate, and all-weather imaging and has received extensive attention in the non-destructive testing and internal imaging applications of layered dielectric targets. However, the non-ideal scattering effect caused by dielectric materials can significantly deteriorate the imaging quality when using the existing MIMO-SAR fast algorithms. This paper proposes a rapid, high-quality dielectric target-enhanced imaging algorithm for a new universal non-uniform MIMO-SAR system. The algorithm builds on the existing non-uniform MIMO-SAR dielectric target frequency-domain algorithm (DT-FDA) by constructing a forward sensing operator and incorporating it into the alternating direction method of multipliers (ADMM) framework. This approach avoids large matrix operations while maintaining computational efficiency. By integrating an optimal regularization parameter search, the algorithm enhances the image reconstruction quality of dielectric internal structures or defects. Experimental results show the proposed algorithm outperforms IBP and DT-FDA, achieving better focusing, sidelobe suppression, and 3D imaging accuracy. It yields the lowest image entropy (8.864) and significantly improves efficiency (imaging time: 15.29 s vs. 23295.3 s for IBP).

eess.SP↗

arXiv2024

$\textit{Dirigo}$: A Method to Extract Event Logs for Object-Centric Processes

Real-world processes involve multiple object types with intricate interrelationships. Traditional event logs (in XES format), which record process execution centred around the case notion, are restricted to a single-object perspective, making it difficult to capture the behaviour of multiple objects and their interactions. To address this limitation, object-centric event logs (OCEL) have been introduced to capture both the objects involved in a process and their interactions with events. The object-centric event data (OCED) metamodel extends the OCEL format by further capturing dynamic object attributes and object-to-object relations. Recently OCEL 2.0 has been proposed based on OCED metamodel. Current research on generating OCEL logs requires specific input data sources, and resulting log data often fails to fully conform to OCEL 2.0. Moreover, the generated OCEL logs vary across different representational formats and their quality remains unevaluated. To address these challenges, a set of quality criteria for evaluating OCEL log representations is established. Guided by these criteria, $\textit{Dirigo}$ is proposed -- a method for extracting event logs that not only conforms to OCEL 2.0 but also extends it by capturing the temporal aspect of dynamic object-to-object relations. Object-role Modelling (ORM), a conceptual data modelling technique, is employed to describe the artifact produced at each step of $\textit{Dirigo}$. To validate the applicability of $\textit{Dirigo}$, it is applied to a real-life use case, extracting an event log via simulation. The quality of the log representation of the extracted event log is compared to those of existing OCEL logs using the established quality criteria.

cs.DB↗

arXiv2024

LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

In this paper we introduce LifelongMemory, a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval. LifelongMemory generates concise video activity descriptions of the camera wearer and leverages the zero-shot capabilities of pretrained large language models to perform reasoning over long-form video context. Furthermore, LifelongMemory uses a confidence and explanation module to produce confident, high-quality, and interpretable answers. Our approach achieves state-of-the-art performance on the EgoSchema benchmark for question answering and is highly competitive on the natural language query (NLQ) challenge of Ego4D. Code is available at https://github.com/agentic-learning-ai-lab/lifelong-memory.

cs.CV↗

arXiv2024

Integrated lithium niobate photonic computing circuit based on efficient and high-speed electro-optic conversion

Here we show a photonic computing accelerator utilizing a system-level thin-film lithium niobate circuit which overcomes this limitation. Leveraging the strong electro-optic (Pockels) effect and the scalability of this platform, we demonstrate photonic computation at speeds up to 1.36 TOPS while consuming 0.057 pJ/OP. Our system features more than 100 thin-film lithium niobate high-performance components working synergistically, surpassing state-of-the-art systems on this platform. We further demonstrate binary-classification, handwritten-digit classification, and image classification with remarkable accuracy, showcasing our system's capability of executing real algorithms. Finally, we investigate the opportunities offered by combining our system with a hybrid-integrated distributed feedback laser source and a heterogeneous-integrated modified uni-traveling carrier photodiode. Our results illustrate the promise of thin-film lithium niobate as a computational platform, addressing current bottlenecks in both electronic and photonic computation. Its unique properties of high-performance electro-optic weight encoding and conversion, wafer-scale scalability, and compatibility with integrated lasers and detectors, position thin-film lithium niobate photonics as a valuable complement to silicon photonics, with extensions to applications in ultrafast and power-efficient signal processing and ranging.

physics.optics↗

arXiv2024

Instance-adaptive Zero-shot Chain-of-Thought Prompting

Zero-shot Chain-of-Thought (CoT) prompting emerges as a simple and effective strategy for enhancing the performance of large language models (LLMs) in real-world reasoning tasks. Nonetheless, the efficacy of a singular, task-level prompt uniformly applied across the whole of instances is inherently limited since one prompt cannot be a good partner for all, a more appropriate approach should consider the interaction between the prompt and each instance meticulously. This work introduces an instance-adaptive prompting algorithm as an alternative zero-shot CoT reasoning scheme by adaptively differentiating good and bad prompts. Concretely, we first employ analysis on LLMs through the lens of information flow to detect the mechanism under zero-shot CoT reasoning, in which we discover that information flows from question to prompt and question to rationale jointly influence the reasoning results most. We notice that a better zero-shot CoT reasoning needs the prompt to obtain semantic information from the question then the rationale aggregates sufficient information from the question directly and via the prompt indirectly. On the contrary, lacking any of those would probably lead to a bad one. Stem from that, we further propose an instance-adaptive prompting strategy (IAP) for zero-shot CoT reasoning. Experiments conducted with LLaMA-2, LLaMA-3, and Qwen on math, logic, and commonsense reasoning tasks (e.g., GSM8K, MMLU, Causal Judgement) obtain consistent improvement, demonstrating that the instance-adaptive zero-shot CoT prompting performs better than other task-level methods with some curated prompts or sophisticated procedures, showing the significance of our findings in the zero-shot CoT reasoning mechanism.

cs.CL↗

arXiv2024

High-Order Associative Learning Based on Memristive Circuits for Efficient Learning

Memristive associative learning has gained significant attention for its ability to mimic fundamental biological learning mechanisms while maintaining system simplicity. In this work, we introduce a high-order memristive associative learning framework with a biologically realistic structure. By utilizing memristors as synaptic modules and their state information to bridge different orders of associative learning, our design effectively establishes associations between multiple stimuli and replicates the transient nature of high-order associative learning. In Pavlov's classical conditioning experiments, our design achieves a 230% improvement in learning efficiency compared to previous works, with memristor power consumption in the synaptic modules remaining below 11 μW. In large-scale image recognition tasks, we utilize a 20*20 memristor array to represent images, enabling the system to recognize and label test images with semantic information at 100% accuracy. This scalability across different tasks highlights the framework's potential for a wide range of applications, offering enhanced learning efficiency for current memristor-based neuromorphic systems.

cs.NE↗

arXiv2024

COMET: Towards Partical W4A4KV4 LLMs Serving

Quantization is a widely-used compression technology to reduce the overhead of serving large language models (LLMs) on terminal devices and in cloud data centers. However, prevalent quantization methods, such as 8-bit weight-activation or 4-bit weight-only quantization, achieve limited performance improvements due to poor support for low-precision (e.g., 4-bit) activation. This work, for the first time, realizes practical W4A4KV4 serving for LLMs, fully utilizing the INT4 tensor cores on modern GPUs and reducing the memory bottleneck caused by the KV cache. Specifically, we propose a novel fine-grained mixed-precision quantization algorithm (FMPQ) that compresses most activations into 4-bit with negligible accuracy loss. To support mixed-precision matrix multiplication for W4A4 and W4A8, we develop a highly optimized W4Ax kernel. Our approach introduces a novel mixed-precision data layout to facilitate access and fast dequantization for activation and weight tensors, utilizing the GPU's software pipeline to hide the overhead of data loading and conversion. Additionally, we propose fine-grained streaming multiprocessor (SM) scheduling to achieve load balance across different SMs. We integrate the optimized W4Ax kernel into our inference framework, COMET, and provide efficient management to support popular LLMs such as LLaMA-3-70B. Extensive evaluations demonstrate that, when running LLaMA family models on a single A100-80G-SMX4, COMET achieves a kernel-level speedup of \textbf{$2.88\times$} over cuBLAS and a \textbf{$2.02 \times$} throughput improvement compared to TensorRT-LLM from an end-to-end framework perspective.

cs.AR↗

arXiv2024

A Survey of Low-shot Vision-Language Model Adaptation via Representer Theorem

The advent of pre-trained vision-language foundation models has revolutionized the field of zero/few-shot (i.e., low-shot) image recognition. The key challenge to address under the condition of limited training data is how to fine-tune pre-trained vision-language models in a parameter-efficient manner. Previously, numerous approaches tackling this challenge have been proposed. Meantime, a few survey papers are also published to summarize these works. However, there still lacks a unified computational framework to integrate existing methods together, identify their nature and support in-depth comparison. As such, this survey paper first proposes a unified computational framework from the perspective of Representer Theorem and then derives many of the existing methods by specializing this framework. Thereafter, a comparative analysis is conducted to uncover the differences and relationships between existing methods. Based on the analyses, some possible variants to improve the existing works are presented. As a demonstration, we extend existing methods by modeling inter-class correlation between representers in reproducing kernel Hilbert space (RKHS), which is implemented by exploiting the closed-form solution of kernel ridge regression. Extensive experiments on 11 datasets are conducted to validate the effectiveness of this method. Toward the end of this paper, we discuss the limitations and provide further research directions.

cs.CV↗

arXiv2024

Fusion Matrix Prompt Enhanced Self-Attention Spatial-Temporal Interactive Traffic Forecasting Framework

Recently, spatial-temporal forecasting technology has been rapidly developed due to the increasing demand for traffic management and travel planning. However, existing traffic forecasting models still face the following limitations. On one hand, most previous studies either focus too much on real-world geographic information, neglecting the potential traffic correlation between different regions, or overlook geographical position and only model the traffic flow relationship. On the other hand, the importance of different time slices is ignored in time modeling. Therefore, we propose a Fusion Matrix Prompt Enhanced Self-Attention Spatial-Temporal Interactive Traffic Forecasting Framework (FMPESTF), which is composed of spatial and temporal modules for down-sampling traffic data. The network is designed to establish a traffic fusion matrix considering spatial-temporal heterogeneity as a query to reconstruct a data-driven dynamic traffic data structure, which accurately reveal the flow relationship of nodes in the traffic network. In addition, we introduce attention mechanism in time modeling, and design hierarchical spatial-temporal interactive learning to help the model adapt to various traffic scenarios. Through extensive experimental on six real-world traffic datasets, our method is significantly superior to other baseline models, demonstrating its efficiency and accuracy in dealing with traffic forecasting problems.

cs.LG↗