arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 703 records · Page 39Linked to original sources

arXiv2024

NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction

Reconstruction of static visual stimuli from non-invasion brain activity fMRI achieves great success, owning to advanced deep learning models such as CLIP and Stable Diffusion. However, the research on fMRI-to-video reconstruction remains limited since decoding the spatiotemporal perception of continuous visual experiences is formidably challenging. We contend that the key to addressing these challenges lies in accurately decoding both high-level semantics and low-level perception flows, as perceived by the brain in response to video stimuli. To the end, we propose NeuroClips, an innovative framework to decode high-fidelity and smooth video from fMRI. NeuroClips utilizes a semantics reconstructor to reconstruct video keyframes, guiding semantic accuracy and consistency, and employs a perception reconstructor to capture low-level perceptual details, ensuring video smoothness. During inference, it adopts a pre-trained T2V diffusion model injected with both keyframes and low-level perception flows for video reconstruction. Evaluated on a publicly available fMRI-video dataset, NeuroClips achieves smooth high-fidelity video reconstruction of up to 6s at 8FPS, gaining significant improvements over state-of-the-art models in various metrics, e.g., a 128% improvement in SSIM and an 81% improvement in spatiotemporal metrics. Our project is available at https://github.com/gongzix/NeuroClips.

eess.IV↗

arXiv2024

Virtualization & Microservice Architecture for Software-Defined Vehicles: An Evaluation and Exploration

The emergence of Software-Defined Vehicles (SDVs) signifies a shift from a distributed network of electronic control units (ECUs) to a centralized computing architecture within the vehicle's electrical and electronic systems. This transition addresses the growing complexity and demand for enhanced functionality in traditional E/E architectures, with containerization and virtualization streamlining software development and updates within the SDV framework. While widely used in cloud computing, their performance and suitability for intelligent vehicles have yet to be thoroughly evaluated. In this work, we conduct a comprehensive performance evaluation of containerization and virtualization on embedded and high-performance AMD64 and ARM64 systems, focusing on CPU, memory, network, and disk metrics. In addition, we assess their impact on real-world automotive applications using the Autoware framework and further integrate a microservice-based architecture to evaluate its start-up time and resource consumption. Our extensive experiments reveal a slight 0-5% performance decline in CPU, memory, and network usage for both containerization and virtualization compared to bare-metal setups, with more significant reductions in disk operations-5-15% for containerized environments and up to 35% for virtualized setups. Despite these declines, experiments with actual vehicle applications demonstrate minimal impact on the Autoware framework, and in some cases, a microservice architecture integration improves start-up time by up to 18%.

cs.RO↗

arXiv2024

A hybrid deep learning method for finite-horizon mean-field game problems

This paper develops a new deep learning algorithm to solve a class of finite-horizon mean-field games. The proposed hybrid algorithm uses Markov chain approximation method combined with a stochastic approximation-based iterative deep learning algorithm. Under the framework of finite-horizon mean-field games, the induced measure and Monte-Carlo algorithm are adopted to establish the iterative mean-field interaction in Markov chain approximation method and deep learning, respectively. The Markov chain approximation method plays a key role in constructing the iterative algorithm and estimating an initial value of a neural network, whereas stochastic approximation is used to find accurate parameters in a bounded region. The convergence of the hybrid algorithm is proved; two numerical examples are provided to illustrate the results.

math.OC↗

arXiv2024

Filling Memory Gaps: Enhancing Continual Semantic Parsing via SQL Syntax Variance-Guided LLMs without Real Data Replay

Continual Semantic Parsing (CSP) aims to train parsers to convert natural language questions into SQL across tasks with limited annotated examples, adapting to the real-world scenario of dynamically updated databases. Previous studies mitigate this challenge by replaying historical data or employing parameter-efficient tuning (PET), but they often violate data privacy or rely on ideal continual learning settings. To address these problems, we propose a new Large Language Model (LLM)-Enhanced Continuous Semantic Parsing method, named LECSP, which alleviates forgetting while encouraging generalization, without requiring real data replay or ideal settings. Specifically, it first analyzes the commonalities and differences between tasks from the SQL syntax perspective to guide LLMs in reconstructing key memories and improving memory accuracy through a calibration strategy. Then, it uses a task-aware dual-teacher distillation framework to promote the accumulation and transfer of knowledge during sequential training. Experimental results on two CSP benchmarks show that our method significantly outperforms existing methods, even those utilizing data replay or ideal settings. Additionally, we achieve generalization performance beyond the upper limits, better adapting to unseen tasks.

cs.CL↗

arXiv2024

SmartReco: Detecting Read-Only Reentrancy via Fine-Grained Cross-DApp Analysis

Despite the increasing popularity of Decentralized Applications (DApps), they are suffering from various vulnerabilities that can be exploited by adversaries for profits. Among such vulnerabilities, Read-Only Reentrancy (called ROR in this paper), is an emerging type of vulnerability that arises from the complex interactions between DApps. In the recent three years, attack incidents of ROR have already caused around 30M USD losses to the DApp ecosystem. Existing techniques for vulnerability detection in smart contracts can hardly detect Read-Only Reentrancy attacks, due to the lack of tracking and analyzing the complex interactions between multiple DApps. In this paper, we propose SmartReco, a new framework for detecting Read-Only Reentrancy vulnerability in DApps through a novel combination of static and dynamic analysis (i.e., fuzzing) over smart contracts. The key design behind SmartReco is threefold: (1) SmartReco identifies the boundary between different DApps from the heavy-coupled cross-contract interactions. (2) SmartReco performs fine-grained static analysis to locate points of interest (i.e., entry functions) that may lead to ROR. (3) SmartReco utilizes the on-chain transaction data and performs multi-function fuzzing (i.e., the entry function and victim function) across different DApps to verify the existence of ROR. Our evaluation of a manual-labeled dataset with 45 RORs shows that SmartReco achieves a precision of 88.63% and a recall of 86.36%. In addition, SmartReco successfully detects 43 new RORs from 123 popular DApps. The total assets affected by such RORs reach around 520,000 USD.

cs.SE↗

arXiv2024

Pattern Tree: Enhancing Efficiency in Quantum Circuit Optimization Based on Pattern-matching

Quantum circuit optimization is essential for improving the performance of quantum algorithms, particularly on Noisy Intermediate-Scale Quantum (NISQ) devices with limited qubit connectivity and high error rates. Pattern matching has proven to be an effective technique for identifying and optimizing subcircuits by replacing them with functionally equivalent, efficient versions, including reducing circuit depth and facilitating platform portability. However, existing approaches face challenges in handling large-scale circuits and numerous transformation rules, often leading to redundant matches and increased compilation time. In this study, we propose a novel framework for quantum circuit optimization based on pattern matching to enhance its efficiency. Observing redundancy in applying existing transformation rules, our method employs a pattern tree structure to organize these rules, reducing redundant operations during the execution of the pattern-matching algorithm and improving matching efficiency. We design and implement a compilation framework to demonstrate the practicality of the pattern tree approach. Experimental results show that pattern-tree-based pattern matching can reduce execution time by an average of 20% on a well-accepted benchmark set. Furthermore, we analyze how to build a pattern tree to maximize the optimization of compilation time. The evaluation results demonstrate that our approach has the potential to optimize compilation time by 90%.

quant-ph↗

arXiv2024

Battery swapping station location for electric vehicles: a simulation optimization approach

Electric vehicles face significant energy supply challenges due to long charging times and congestion at charging stations. Battery swapping stations (BSSs) offer a faster alternative for energy replenishment, but their deployment costs are considerably higher than those of charging stations. As a result, selecting optimal locations for BSSs is crucial to improve their accessibility and utilization. Most existing studies model the BSS location problem using deterministic and static approaches, often overlooking the impact of stochastic and dynamic factors on solution quality. This paper addresses the facility location problem for BSSs within a city network, considering stochastic battery swapping demand. The objective is to optimize the placement of a given set of BSSs to minimize demand loss. To achieve this, we first develop a mathematical programming model for the problem. Then, we propose a simulation optimization method based on a large neighborhood search framework to handle large-scale instances. To reduce the computational cost of simulations, Bayesian optimization is employed to solve the single-station allocation subproblem during the repair process. Numerical experiments demonstrate the efficiency of the proposed approach and highlight the importance of incorporating dynamic factors in decision-making.

math.OC↗

arXiv2024

4D SlingBAG: spatial-temporal coupled Gaussian ball for large-scale dynamic 3D photoacoustic iterative reconstruction

Large-scale dynamic three-dimensional (3D) photoacoustic imaging (PAI) is significantly important in clinical applications. In practical implementations, large-scale 3D real-time PAI systems typically utilize sparse two-dimensional (2D) sensor arrays with certain angular deficiencies, necessitating advanced iterative reconstruction (IR) algorithms to achieve quantitative PAI and reduce reconstruction artifacts. However, for existing IR algorithms, multi-frame 3D reconstruction leads to extremely high memory consumption and prolonged computation time, with limited consideration of the spatial-temporal continuity between data frames. Here, we propose a novel method, named the 4D sliding Gaussian ball adaptive growth (4D SlingBAG) algorithm, based on the current point cloud-based IR algorithm sliding Gaussian ball adaptive growth (SlingBAG), which has minimal memory consumption among IR methods. Our 4D SlingBAG method applies spatial-temporal coupled deformation functions to each Gaussian sphere in point cloud, thus explicitly learning the deformations features of the dynamic 3D PA scene. This allows for the efficient representation of various physiological processes (such as pulsation) or external pressures (e.g., blood perfusion experiments) contributing to changes in vessel morphology and blood flow during dynamic 3D PAI, enabling highly efficient IR for dynamic 3D PAI. Simulation experiments demonstrate that 4D SlingBAG achieves high-quality dynamic 3D PA reconstruction. Compared to performing reconstructions by using SlingBAG algorithm individually for each frame, our method significantly reduces computational time and keeps a extremely low memory consumption. The project for 4D SlingBAG can be found in the following GitHub repository: \href{https://github.com/JaegerCQ/4D-SlingBAG}{https://github.com/JaegerCQ/4D-SlingBAG}.

cs.CV↗

arXiv2024

Calibration of cascaded phase shifters using pairwise scan method in silicon photonics integrated chip

Cascaded phase shifters (CPSs) based on silicon photonics integrated chips play important roles in quantum information processing tasks. Owing to an increase in the scale of silicon photonics chips, the time required to calibrate various CPSs has increased. We propose a pairwise scan method for rapidly calibrating CPSs by introducing equivalent Mach Zehnder Interferometer structures and a reasonable constraint of the initial relative phase. The calibration can be nearly completed when the scanning process is finished, and only a little calculation is required. To achieve better performance, the key components, thermal optical phase shifter and 2 * 2 50/50 multimode interference coupler, were simulated and optimized to prevent thermal crosstalk and ensure a good balance. A 6-CPSs structure in a packaged silicon photonics chip under different temperature was used to verify the rapid pairwise scan method, and a fidelity of 99.97% was achieved.

quant-ph↗

arXiv2024

BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognition

Despite the recent success of two-stage prototypical networks in few-shot named entity recognition (NER), challenges such as over/under-detected false spans in the span detection stage and unaligned entity prototypes in the type classification stage persist. Additionally, LLMs have not proven to be effective few-shot information extractors in general. In this paper, we propose an approach called Boundary-Aware LLMs for Few-Shot Named Entity Recognition to address these issues. We introduce a boundary-aware contrastive learning strategy to enhance the LLM's ability to perceive entity boundaries for generalized entity spans. Additionally, we utilize LoRAHub to align information from the target domain to the source domain, thereby enhancing adaptive cross-domain classification capabilities. Extensive experiments across various benchmarks demonstrate that our framework outperforms prior methods, validating its effectiveness. In particular, the proposed strategies demonstrate effectiveness across a range of LLM architectures. The code and data are released on https://github.com/UESTC-GQJ/BANER.

cs.CL↗

arXiv2024

Ultra low-cost fabrication of homogeneous alginate hydrogel microspheres in symmetry designed microfluidic device

In this study, we present a two-stage method for fabricating monodisperse alginate hydrogel microspheres using a symmetrically designed flow-focusing microfluidic device. One of the flow-focusing junctions generates alginate hydrogel droplets without the addition of surfactants, while the other junction introduces corn oil with acetic acid, which facilitates the solidification of the homogeneous alginate hydrogel droplets and prevents coalescence. These hydrogel microspheres can be easily separated from the oil phase using an oscillation state, eliminating the need for a demulsifier. This microfluidic system for hydrogel microsphere formation is notable for its simplicity, ease of fabrication, and user-friendliness.

physics.chem-ph↗

arXiv2024

CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention

Vehicle Routing Problems (VRPs) are significant Combinatorial Optimization (CO) problems holding substantial practical importance. Recently, Neural Combinatorial Optimization (NCO), which involves training deep learning models on extensive data to learn vehicle routing heuristics, has emerged as a promising approach due to its efficiency and the reduced need for manual algorithm design. However, applying NCO across diverse real-world scenarios with various constraints necessitates cross-problem capabilities. Current NCO methods typically employ a unified model lacking a constraint-specific structure, thereby restricting their cross-problem performance. Current multi-task methods for VRPs typically employ a constraint-unaware model, limiting their cross-problem performance. Furthermore, they rely solely on global connectivity, which fails to focus on key nodes and leads to inefficient representation learning. This paper introduces a Constraint-Aware Dual-Attention Model (CaDA), designed to address these limitations. CaDA incorporates a constraint prompt that efficiently represents different problem variants. Additionally, it features a dual-attention mechanism with a global branch for capturing broader graph-wide information and a sparse branch that selectively focuses on the most relevant nodes. We comprehensively evaluate our model on 16 different VRPs and compare its performance against existing cross-problem VRP solvers. CaDA achieves state-of-the-art results across all the VRPs. Our ablation study further confirms that each component of CaDA contributes positively to its cross-problem learning performance.

cs.AI↗

arXiv2024

MV4PG: Materialized Views for Property Graphs

Graph databases are getting more and more attention in the highly interconnected data domain, and the demand for efficient querying of big data is increasing. We noticed that there are duplicate patterns in graph database queries, and the results of these patterns can be stored as materialized views first, which can speed up the query rate. So we propose materialized views on property graphs, including three parts: view creation, view maintenance, and query optimization using views, and we propose for the first time an efficient templated view maintenance method for containing variable-length edges, which can be applied to multiple graph databases. In order to verify the effect of materialized views, we prototype on TuGraph and experiment on both TuGraph and Neo4j. The experiment results show that our query optimization on read statements is much higher than the additional view maintenance cost brought by write statements. The speedup ratio of the whole workload reaches up to 28.71x, and the speedup ratio of a single query reaches up to nearly 100x.

cs.DB↗

arXiv2024

From RNNs to Foundation Models: An Empirical Study on Commercial Building Energy Consumption

Accurate short-term energy consumption forecasting for commercial buildings is crucial for smart grid operations. While smart meters and deep learning models enable forecasting using past data from multiple buildings, data heterogeneity from diverse buildings can reduce model performance. The impact of increasing dataset heterogeneity in time series forecasting, while keeping size and model constant, is understudied. We tackle this issue using the ComStock dataset, which provides synthetic energy consumption data for U.S. commercial buildings. Two curated subsets, identical in size and region but differing in building type diversity, are used to assess the performance of various time series forecasting models, including fine-tuned open-source foundation models (FMs). The results show that dataset heterogeneity and model architecture have a greater impact on post-training forecasting performance than the parameter count. Moreover, despite the higher computational cost, fine-tuned FMs demonstrate competitive performance compared to base models trained from scratch.

cs.LG↗

arXiv2024

MixPE: Quantization and Hardware Co-design for Efficient LLM Inference

Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computational and memory demands. Quantization has emerged as a promising solution, and state-of-the-art quantization algorithms for LLMs introduce the need for mixed-precision matrix multiplication (mpGEMM), where lower-precision weights are multiplied with higher-precision activations. Despite its benefits, current hardware accelerators such as GPUs and TPUs lack native support for efficient mpGEMM, leading to inefficient dequantization operations in the main sequential loop. To address this limitation, we introduce MixPE, a specialized mixed-precision processing element designed for efficient low-bit quantization in LLM inference. MixPE leverages two key innovations to minimize dequantization overhead and unlock the full potential of low-bit quantization. First, recognizing that scale and zero point are shared within each quantization group, we propose performing dequantization after per-group mpGEMM, significantly reducing dequantization overhead. Second, instead of relying on conventional multipliers, MixPE utilizes efficient shift\&add operations for multiplication, optimizing both computation and energy efficiency. Our experimental results demonstrate that MixPE surpasses the state-of-the-art quantization accelerators by $2.6\times$ speedup and $1.4\times$ energy reduction.

cs.LG↗

arXiv2024

Gassidy: Gaussian Splatting SLAM in Dynamic Environments

3D Gaussian Splatting (3DGS) allows flexible adjustments to scene representation, enabling continuous optimization of scene quality during dense visual simultaneous localization and mapping (SLAM) in static environments. However, 3DGS faces challenges in handling environmental disturbances from dynamic objects with irregular movement, leading to degradation in both camera tracking accuracy and map reconstruction quality. To address this challenge, we develop an RGB-D dense SLAM which is called Gaussian Splatting SLAM in Dynamic Environments (Gassidy). This approach calculates Gaussians to generate rendering loss flows for each environmental component based on a designed photometric-geometric loss function. To distinguish and filter environmental disturbances, we iteratively analyze rendering loss flows to detect features characterized by changes in loss values between dynamic objects and static components. This process ensures a clean environment for accurate scene reconstruction. Compared to state-of-the-art SLAM methods, experimental results on open datasets show that Gassidy improves camera tracking precision by up to 97.9% and enhances map quality by up to 6%.

cs.RO↗

arXiv2024

Light-Matter Hybridization and Entanglement from the First-Principles

The hybridization between light and matter is fundamental for achieving cavity-induced control over quantum materials, necessitating accurate ab initio methods for their analysis. Among these, the quantum electrodynamics Hartree-Fock framework stands out as an essential mean field approximation for electron-electron and electron-photon interactions, forming the basis for advanced post-Hartree-Fock methods like quantum electrodynamics coupled cluster and auxiliary field quantum Monte Carlo. However, trivial quantum electrodynamics Hartere-Fock (QEDHF) methods assume a product state ansätze and thus cannot describe the light-matter Entanglement. Furthermore, our previous work on variational ansätze approaches lacked the capability to capture anharmonic or nonlinear fluctuations, limiting their applicability to strongly coupled systems. To overcome these limitations, we propose an extended QEDHF formalism by introducing a variational Squeeze transformation capable of describing anharmonic quantum fluctuations in photon fields. By optimizing the squeezing parameters, our framework provides a more nuanced and accurate characterization of photon field quantum fluctuations, significantly enhancing the predictive power of QEDHF in strong coupling regimes. Moreover, this formalism enhances the description of light-matter Entanglement, providing a first-principles framework for understanding light-matter hybridization and paving the way for deeper insights into cavity-modified quantum phenomena.

quant-ph↗

arXiv2024

Many-body nonequilibrium dynamics in a self-induced Floquet system

Floquet systems are periodically driven systems. In this framework, the system Hamiltonian and associated spectra of interest are modified, giving rise to new quantum phases of matter and nonequilibrium dynamics without static counterparts. Here we experimentally demonstrate a self-induced Floquet system in the interacting Rydberg gas. This originates from the photoionization of thermal Rydberg gases in a static magnetic field. Importantly, by leveraging the Rydberg electromagnetically induced transparency spectrum, we probe the nonequilibrium dynamics in the bistable regime and identify the emergence of a discrete time crystalline phase. Our work fills the experimental gap in the understanding the relation of multistability and dissipative discrete time crystalline phase. In this regard, it constitutes a highly controlled platform for exploring exotic nonequilibrium physics in dissipative interacting systems.

quant-ph↗