arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 703 records · Page 39Linked to original sources

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↗

arXiv2024

Normative Modeling for AD Diagnosis and Biomarker Identification

In this paper, we introduce a novel normative modeling approach that incorporates focal loss and adversarial autoencoders (FAAE) for Alzheimer's Disease (AD) diagnosis and biomarker identification. Our method is an end-to-end approach that embeds an adversarial focal loss discriminator within the autoencoder structure, specifically designed to effectively target and capture more complex and challenging cases. We first use the enhanced autoencoder to create a normative model based on data from healthy control (HC) individuals. We then apply this model to estimate total and regional neuroanatomical deviation in AD patients. Through extensive experiments on the OASIS-3 and ADNI datasets, our approach significantly outperforms previous state-of-the-art methods. This advancement not only streamlines the detection process but also provides a greater insight into the biomarker potential for AD. Our code can be found at \url{https://github.com/soz223/FAAE}.

eess.IV↗

arXiv2024

Enhanced Classroom Dialogue Sequences Analysis with a Hybrid AI Agent: Merging Expert Rule-Base with Large Language Models

Classroom dialogue plays a crucial role in fostering student engagement and deeper learning. However, analysing dialogue sequences has traditionally relied on either theoretical frameworks or empirical descriptions of practice, with limited integration between the two. This study addresses this gap by developing a comprehensive rule base of dialogue sequences and an Artificial Intelligence (AI) agent that combines expert-informed rule-based systems with a large language model (LLM). The agent applies expert knowledge while adapting to the complexities of natural language, enabling accurate and flexible categorisation of classroom dialogue sequences. By synthesising findings from over 30 studies, we established a comprehensive framework for dialogue analysis. The agent was validated against human expert coding, achieving high levels of precision and reliability. The results demonstrate that the agent provides theory-grounded and adaptive functions, tremendously enhancing the efficiency and scalability of classroom dialogue analysis, offering significant potential in improving classroom teaching practices and supporting teacher professional development.

cs.AI↗

arXiv2024

HomoMatcher: Dense Feature Matching Results with Semi-Dense Efficiency by Homography Estimation

Feature matching between image pairs is a fundamental problem in computer vision that drives many applications, such as SLAM. Recently, semi-dense matching approaches have achieved substantial performance enhancements and established a widely-accepted coarse-to-fine paradigm. However, the majority of existing methods focus on improving coarse feature representation rather than the fine-matching module. Prior fine-matching techniques, which rely on point-to-patch matching probability expectation or direct regression, often lack precision and do not guarantee the continuity of feature points across sequential images. To address this limitation, this paper concentrates on enhancing the fine-matching module in the semi-dense matching framework. We employ a lightweight and efficient homography estimation network to generate the perspective mapping between patches obtained from coarse matching. This patch-to-patch approach achieves the overall alignment of two patches, resulting in a higher sub-pixel accuracy by incorporating additional constraints. By leveraging the homography estimation between patches, we can achieve a dense matching result with low computational cost. Extensive experiments demonstrate that our method achieves higher accuracy compared to previous semi-dense matchers. Meanwhile, our dense matching results exhibit similar end-point-error accuracy compared to previous dense matchers while maintaining semi-dense efficiency.

cs.CV↗

arXiv2024

CROLoss: Towards a Customizable Loss for Retrieval Models in Recommender Systems

In large-scale recommender systems, retrieving top N relevant candidates accurately with resource constrain is crucial. To evaluate the performance of such retrieval models, Recall@N, the frequency of positive samples being retrieved in the top N ranking, is widely used. However, most of the conventional loss functions for retrieval models such as softmax cross-entropy and pairwise comparison methods do not directly optimize Recall@N. Moreover, those conventional loss functions cannot be customized for the specific retrieval size N required by each application and thus may lead to sub-optimal performance. In this paper, we proposed the Customizable Recall@N Optimization Loss (CROLoss), a loss function that can directly optimize the Recall@N metrics and is customizable for different choices of N. This proposed CROLoss formulation defines a more generalized loss function space, covering most of the conventional loss functions as special cases. Furthermore, we develop the Lambda method, a gradient-based method that invites more flexibility and can further boost the system performance. We evaluate the proposed CROLoss on two public benchmark datasets. The results show that CROLoss achieves SOTA results over conventional loss functions for both datasets with various choices of retrieval size N. CROLoss has been deployed onto our online E-commerce advertising platform, where a fourteen-day online A/B test demonstrated that CROLoss contributes to a significant business revenue growth of 4.75%.

cs.IR↗

arXiv2024

Coalescence induced late departure of bubbles improves water electrolysis efficiency

In water electrolysis, bubbles form on the electrode and interact through processes such as collision and coalescence. However, the impact of bubble coalescence a fundamental process governing electrolytic bubble behaviour-on electrolysis efficiency remains unclear. Here, we show that enhancing bubble coalescence improves electrolysis efficiency by more than 30% compared to systems where coalescence is inhibited. One key feature is the continuous coalescence of a newly detached bubble with microbubbles on the electrode, which delays the former from departing. Experimental observations and numerical simulations reveal two key benefits of bubble coalescence for electrolysis efficiency: (1) it liberates surface bubbles from the electrode at much smaller sizes, reducing their diameter from approximately 60-80 um to less than 10 um, thus freeing the active sites of the electrode from bubble coverage; (2) it induces strong agitation, with velocities reaching 1m/s in a small region near the electrode (at a depth of 10-5 m), thereby significantly improving the heat/mass transfer locally. Importantly, the chaotic agitation effect lasts for approximately 10 ms, two orders of magnitude longer than the coalescence process, which occurs in around 0.2 ms. This work provides valuable insight into bubble management in water electrolysis and other gas-evolution electrochemical reactions.

physics.chem-ph↗

arXiv2024

Sliding Gaussian ball adaptive growth (SlingBAG): point cloud-based iterative algorithm for large-scale 3D photoacoustic imaging

Large-scale 3D photoacoustic (PA) imaging has become increasingly important for both clinical and pre-clinical applications. Limited by cost and system complexity, only systems with sparsely-distributed sensors can be widely implemented, which desires advanced reconstruction algorithms to reduce artifacts. However, high computing memory and time consumption of traditional iterative reconstruction (IR) algorithms is practically unacceptable for large-scale 3D PA imaging. Here, we propose a point cloud-based IR algorithm that reduces memory consumption by several orders, wherein the 3D PA scene is modeled as a series of Gaussian-distributed spherical sources stored in form of point cloud. During the IR process, not only are properties of each Gaussian source, including its peak intensity (initial pressure value), standard deviation (size) and mean (position) continuously optimized, but also each Gaussian source itself adaptively undergoes destroying, splitting, and duplication along the gradient direction. This method, named the sliding Gaussian ball adaptive growth (SlingBAG) algorithm, enables high-quality large-scale 3D PA reconstruction with fast iteration and extremely low memory usage. We validated SlingBAG algorithm in both simulation study and in vivo animal experiments. The source code and data for SlingBAG, along with supplementary materials and demonstration videos, are now available in the following GitHub repository: https://github.com/JaegerCQ/SlingBAG.

cs.CV↗

arXiv2024

TileTracker: Tracking Based Vector HD Mapping using Top-Down Road Images

In this paper, we propose a tracking-based HD mapping algorithm for top-down road images, referred to as tile images. While HD maps traditionally rely on perspective camera images, our approach shows that tile images can also be effectively utilized, offering valuable contributions to this research area as it can be start of a new path in HD mapping algorithms. We modified the BEVFormer layers to generate BEV masks from tile images, which are then used by the model to generate divider and boundary lines. Our model was tested with both color and intensity images, and we present quantitative and qualitative results to demonstrate its performance.

cs.CV↗

arXiv2024

Map++: Towards User-Participatory Visual SLAM Systems with Efficient Map Expansion and Sharing

Constructing precise 3D maps is crucial for the development of future map-based systems such as self-driving and navigation. However, generating these maps in complex environments, such as multi-level parking garages or shopping malls, remains a formidable challenge. In this paper, we introduce a participatory sensing approach that delegates map-building tasks to map users, thereby enabling cost-effective and continuous data collection. The proposed method harnesses the collective efforts of users, facilitating the expansion and ongoing update of the maps as the environment evolves. We realized this approach by developing Map++, an efficient system that functions as a plug-and-play extension, supporting participatory map-building based on existing SLAM algorithms. Map++ addresses a plethora of scalability issues in this participatory map-building system by proposing a set of lightweight, application-layer protocols. We evaluated Map++ in four representative settings: an indoor garage, an outdoor plaza, a public SLAM benchmark, and a simulated environment. The results demonstrate that Map++ can reduce traffic volume by approximately 46% with negligible degradation in mapping accuracy, i.e., less than 0.03m compared to the baseline system. It can support approximately $2 \times$ as many concurrent users as the baseline under the same network bandwidth. Additionally, for users who travel on already-mapped trajectories, they can directly utilize the existing maps for localization and save 47% of the CPU usage.

cs.CV↗

arXiv2024

GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning

Large Language Models (LLMs) are increasingly used for various tasks with graph structures. Though LLMs can process graph information in a textual format, they overlook the rich vision modality, which is an intuitive way for humans to comprehend structural information and conduct general graph reasoning. The potential benefits and capabilities of representing graph structures as visual images (i.e., $\textit{visual graph}$) are still unexplored. To fill the gap, we innovatively propose an end-to-end framework, called $\textbf{G}$raph to v$\textbf{I}$sual and $\textbf{T}$extual Integr$\textbf{A}$tion (GITA), which firstly incorporates visual graphs into general graph reasoning. Besides, we establish $\textbf{G}$raph-based $\textbf{V}$ision-$\textbf{L}$anguage $\textbf{Q}$uestion $\textbf{A}$nswering (GVLQA) dataset from existing graph data, which is the first vision-language dataset for general graph reasoning purposes. Extensive experiments on the GVLQA dataset and five real-world datasets show that GITA outperforms mainstream LLMs in terms of general graph reasoning capabilities. Moreover, We highlight the effectiveness of the layout augmentation on visual graphs and pretraining on the GVLQA dataset.

cs.CL↗