arXiv subjects

Xin Zhang

Publications and source records attributed to Xin Zhang.

At least 613 records · Page 34Linked to original sources

arXiv2024

Potential of Multimodal Large Language Models for Data Mining of Medical Images and Free-text Reports

Medical images and radiology reports are crucial for diagnosing medical conditions, highlighting the importance of quantitative analysis for clinical decision-making. However, the diversity and cross-source heterogeneity of these data challenge the generalizability of current data-mining methods. Multimodal large language models (MLLMs) have recently transformed many domains, significantly affecting the medical field. Notably, Gemini-Vision-series (Gemini) and GPT-4-series (GPT-4) models have epitomized a paradigm shift in Artificial General Intelligence (AGI) for computer vision, showcasing their potential in the biomedical domain. In this study, we evaluated the performance of the Gemini, GPT-4, and 4 popular large models for an exhaustive evaluation across 14 medical imaging datasets, including 5 medical imaging categories (dermatology, radiology, dentistry, ophthalmology, and endoscopy), and 3 radiology report datasets. The investigated tasks encompass disease classification, lesion segmentation, anatomical localization, disease diagnosis, report generation, and lesion detection. Our experimental results demonstrated that Gemini-series models excelled in report generation and lesion detection but faces challenges in disease classification and anatomical localization. Conversely, GPT-series models exhibited proficiency in lesion segmentation and anatomical localization but encountered difficulties in disease diagnosis and lesion detection. Additionally, both the Gemini series and GPT series contain models that have demonstrated commendable generation efficiency. While both models hold promise in reducing physician workload, alleviating pressure on limited healthcare resources, and fostering collaboration between clinical practitioners and artificial intelligence technologies, substantial enhancements and comprehensive validations remain imperative before clinical deployment.

eess.IV↗

arXiv2024

Exact solution of a two-parameter extended Bariev model

An exactly solvable strongly correlated electron model with two independent parameters is constructed in the frame of the quantum inverse scattering method, which can be seen as a generalization of the Bariev model. Through the Bethe ansatz method, a set of Bethe ansatz equations is derived. In the thermodynamic limit, to study the ground state of the model, we obtain the integral equations for the density of Bethe roots. Numerical validation are done to confirm the accuracy of our analytic results.

cond-mat.str-el↗

arXiv2024

Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing

Enhancing diverse human decision-making processes in an urban environment is a critical issue across various applications, including ride-sharing vehicle dispatching, public transportation management, and autonomous driving. Offline reinforcement learning (RL) is a promising approach to learn and optimize human urban strategies (or policies) from pre-collected human-generated spatial-temporal urban data. However, standard offline RL faces two significant challenges: (1) data scarcity and data heterogeneity, and (2) distributional shift. In this paper, we introduce MODA -- a Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing approach. MODA addresses the challenges of data scarcity and heterogeneity in a multi-task urban setting through Contrastive Data Sharing among tasks. This technique involves extracting latent representations of human behaviors by contrasting positive and negative data pairs. It then shares data presenting similar representations with the target task, facilitating data augmentation for each task. Moreover, MODA develops a novel model-based multi-task offline RL algorithm. This algorithm constructs a robust Markov Decision Process (MDP) by integrating a dynamics model with a Generative Adversarial Network (GAN). Once the robust MDP is established, any online RL or planning algorithm can be applied. Extensive experiments conducted in a real-world multi-task urban setting validate the effectiveness of MODA. The results demonstrate that MODA exhibits significant improvements compared to state-of-the-art baselines, showcasing its capability in advancing urban decision-making processes. We also made our code available to the research community.

cs.LG↗

arXiv2024

GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networks

Massive number of applications involve data with underlying relationships embedded in non-Euclidean space. Graph neural networks (GNNs) are utilized to extract features by capturing the dependencies within graphs. Despite groundbreaking performances, we argue that Multi-layer perceptrons (MLPs) and fixed activation functions impede the feature extraction due to information loss. Inspired by Kolmogorov Arnold Networks (KANs), we make the first attempt to GNNs with KANs. We discard MLPs and activation functions, and instead used KANs for feature extraction. Experiments demonstrate the effectiveness of GraphKAN, emphasizing the potential of KANs as a powerful tool. Code is available at https://github.com/Ryanfzhang/GraphKan.

cs.LG↗

arXiv2024

AutoSurvey: Large Language Models Can Automatically Write Surveys

This paper introduces AutoSurvey, a speedy and well-organized methodology for automating the creation of comprehensive literature surveys in rapidly evolving fields like artificial intelligence. Traditional survey paper creation faces challenges due to the vast volume and complexity of information, prompting the need for efficient survey methods. While large language models (LLMs) offer promise in automating this process, challenges such as context window limitations, parametric knowledge constraints, and the lack of evaluation benchmarks remain. AutoSurvey addresses these challenges through a systematic approach that involves initial retrieval and outline generation, subsection drafting by specialized LLMs, integration and refinement, and rigorous evaluation and iteration. Our contributions include a comprehensive solution to the survey problem, a reliable evaluation method, and experimental validation demonstrating AutoSurvey's effectiveness.We open our resources at \url{https://github.com/AutoSurveys/AutoSurvey}.

cs.IR↗

arXiv2024

Video Frame Interpolation for Polarization via Swin-Transformer

Video Frame Interpolation (VFI) has been extensively explored and demonstrated, yet its application to polarization remains largely unexplored. Due to the selective transmission of light by polarized filters, longer exposure times are typically required to ensure sufficient light intensity, which consequently lower the temporal sample rates. Furthermore, because polarization reflected by objects varies with shooting perspective, focusing solely on estimating pixel displacement is insufficient to accurately reconstruct the intermediate polarization. To tackle these challenges, this study proposes a multi-stage and multi-scale network called Swin-VFI based on the Swin-Transformer and introduces a tailored loss function to facilitate the network's understanding of polarization changes. To ensure the practicality of our proposed method, this study evaluates its interpolated frames in Shape from Polarization (SfP) and Human Shape Reconstruction tasks, comparing them with other state-of-the-art methods such as CAIN, FLAVR, and VFIT. Experimental results demonstrate our approach's superior reconstruction accuracy across all tasks.

cs.CV↗

arXiv2024

A comprehensive forecast for cosmological parameter estimation using joint observations of gravitational waves and short $γ$-ray bursts

In the third-generation (3G) gravitational-wave (GW) detector era, the multi-messenger GW observation for binary neutron star (BNS) merger events can exert great impacts on exploring the cosmic expansion history. In this work, we comprehensively explore the potential of 3G GW standard siren observations in cosmological parameter estimations by considering the 3G GW detectors and the future short $γ$-ray burst (GRB) detector THESEUS-like telescope joint observations. Based on the 10-year observation of different detection strategies, we predict that the numbers of detectable GW-GRB events are 334--674 with the redshifts $z<3.5$ and the inclination angles $ι<15^{\circ}$. For the cosmological analysis, we consider the $Λ$CDM, $w$CDM, $w_0w_a$CDM models, and interacting dark energy (IDE) models. We find that GW can tightly constrain the Hubble constant with precisions of $0.345\%-0.065\%$, but perform not well in constraining other cosmological parameters. Fortunately, GW could effectively break the cosmological parameter degeneracies generated by the mainstream EM observations, CMB+BAO+SN (CBS). When combining the mock GW data with the CBS data, CBS+GW can tightly constrain the equation of state of dark energy $w$ with a precision of 1.26\%, close to the standard of precision cosmology. Meanwhile, the addition of GW to CBS could improve constraints on cosmological parameters by $34.2\%-94.9\%$. In conclusion, GW standard siren observations from 3G GW detectors could play a crucial role in helping solve the Hubble tension and probe the fundamental nature of dark energy.

astro-ph.CO↗

arXiv2024

Dynamical and thermodynamic crossovers in the supercritical region of a holographic superfluid model

Many physical systems, including classical fluids, present in their phase diagram the competition between two phases that are separated by a line of first-order phase transitions which terminates at a so-called critical point. Despite several proposals, in the supercritical region beyond the critical point, whether the two phases can still be distinguished and by which criterion remain open questions. In this work, we study the thermodynamics and linear dynamics of a holographic superfluid model with nonlinear potential terms in the supercritical region. We identify the presence of a dynamical crossover, akin to the liquid-like to gas-like Frenkel transition in supercritical fluids, and we define other separation lines of thermodynamic origin based on higher order derivatives of the free energy with respect to the charge density. Our results highlight the universal dynamical and thermodynamic features of supercritical systems from nuclear matter and classical fluids to superfluid systems.

hep-th↗

arXiv2024

WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning

Recent work demonstrates that, after instruction tuning, Code Large Language Models (Code LLMs) can obtain impressive capabilities to address a wide range of code-related tasks. However, current instruction tuning methods for Code LLMs mainly focus on the traditional code generation task, resulting in poor performance in complex multi-task scenarios. In this paper, we concentrate on multiple code-related tasks and present WaveCoder, a series of Code LLMs trained with Widespread And Versatile Enhanced instruction data. To enable the models to tackle complex code-related tasks, we propose a method to stably generate diverse, high-quality instruction data from open source code dataset in multi-task scenarios and obtain CodeSeaXDataset, a dataset comprising 19,915 instruction instances across 4 code-related tasks, which is aimed at improving the generalization ability of Code LLM. Our experiments demonstrate that WaveCoder models significantly outperform other open-source models in terms of the generalization ability across different code-related tasks. Moreover, WaveCoder-Ultra-6.7B presents the state-of-the-art generalization abilities on a wide range of code-related tasks.

cs.CL↗

arXiv2024

ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models

Large Language Models (LLMs) are transforming diverse fields and gaining increasing influence as human proxies. This development underscores the urgent need for evaluating value orientations and understanding of LLMs to ensure their responsible integration into public-facing applications. This work introduces ValueBench, the first comprehensive psychometric benchmark for evaluating value orientations and value understanding in LLMs. ValueBench collects data from 44 established psychometric inventories, encompassing 453 multifaceted value dimensions. We propose an evaluation pipeline grounded in realistic human-AI interactions to probe value orientations, along with novel tasks for evaluating value understanding in an open-ended value space. With extensive experiments conducted on six representative LLMs, we unveil their shared and distinctive value orientations and exhibit their ability to approximate expert conclusions in value-related extraction and generation tasks. ValueBench is openly accessible at https://github.com/Value4AI/ValueBench.

cs.CL↗

arXiv2024

CIRCUITSYNTH: Leveraging Large Language Models for Circuit Topology Synthesis

Circuit topology generation plays a crucial role in the design of electronic circuits, influencing the fundamental functionality of the circuit. In this paper, we introduce CIRCUITSYNTH, a novel approach that harnesses LLMs to facilitate the automated synthesis of valid circuit topologies. With a dataset comprising both valid and invalid circuit configurations, CIRCUITSYNTH employs a sophisticated two-phase methodology, comprising Circuit Topology Generation and Circuit Topology Refinement. Experimental results demonstrate the effectiveness of CIRCUITSYNTH compared to various fine-tuned LLM variants. Our approach lays the foundation for future research aimed at enhancing circuit efficiency and specifying output voltage, thus enabling the automated generation of circuit topologies with improved performance and adherence to design requirements.

cs.LG↗

arXiv2024

Physics Inspired Criterion for Pruning-Quantization Joint Learning

Pruning-quantization joint learning always facilitates the deployment of deep neural networks (DNNs) on resource-constrained edge devices. However, most existing methods do not jointly learn a global criterion for pruning and quantization in an interpretable way. In this paper, we propose a novel physics inspired criterion for pruning-quantization joint learning (PIC-PQ), which is explored from an analogy we first draw between elasticity dynamics (ED) and model compression (MC). Specifically, derived from Hooke's law in ED, we establish a linear relationship between the filters' importance distribution and the filter property (FP) by a learnable deformation scale in the physics inspired criterion (PIC). Furthermore, we extend PIC with a relative shift variable for a global view. To ensure feasibility and flexibility, available maximum bitwidth and penalty factor are introduced in quantization bitwidth assignment. Experiments on benchmarks of image classification demonstrate that PIC-PQ yields a good trade-off between accuracy and bit-operations (BOPs) compression ratio e.g., 54.96X BOPs compression ratio in ResNet56 on CIFAR10 with 0.10% accuracy drop and 53.24X in ResNet18 on ImageNet with 0.61% accuracy drop). The code will be available at https://github.com/fanxxxxyi/PIC-PQ.

cs.LG↗

arXiv2024

All-sky Guide Star Catalog for CSST

The China Space Station Telescope (CSST) is a two-meter space telescope with multiple back-end instruments. The Fine Guidance Sensor (FGS) is an essential subsystem of the CSST Precision Image Stability System to ensure the required absolute pointing accuracy and line-of-sight stabilization. In this study, we construct the Main Guide Star Catalog for FGS. To accomplish this, we utilize the information about the FGS and object information from the Gaia Data Release 3. We provide an FGS instrument magnitude and exclude variables, binaries, and high proper motion stars from the catalog to ensure uniform FGS guidance capabilities. Subsequently, we generate a HEALPix index, which provides a hierarchical tessellation of the celestial sphere, and employ the Voronoi algorithm to achieve a homogeneous distribution of stars across the catalog. This distribution ensures adequate coverage and sampling of the sky. The performance of the CSST guide star catalog was assessed by simulating the field of view of the FGS according to the CSST mock survey strategy catalog. The analysis of the results indicates that this catalog provides adequate coverage and accuracy. The catalog's performance meets the FGS requirements, ensuring the functioning of the FGS and its guidance capabilities.

astro-ph.IM↗

arXiv2024

Quantum accelerated cross regression algorithm for multiview feature extraction

Multi-view Feature Extraction (MvFE) has wide applications in machine learning, image processing and other fields. When dealing with massive high-dimensional data, the performance of classical computer faces severe challenges due to MvFE involves expensive matrix calculation. To address this challenge, a quantum-accelerated cross-regression algorithm for MvFE is proposed. The main contributions are as follows:(1) a quantum version algorithm for MvFE is proposed for the first time, filling the gap of quantum computing in the field of MvFE;(2) a quantum algorithm is designed to construct the block-encoding of the target data matrix, so that the optimal Hamiltonian simulation technology based on the block-encoding framework can be used to efficiently realize the quantum simulation of the target data matrix. This approach reduces the dependence of the algorithm's on simulation errors to enhance algorithm performance;(3) compared with the classical counterpart algorithm, the proposed quantum algorithm has a polynomial acceleration in the number of data points, the dimension of data points and the number of view data.

quant-ph↗

arXiv2024

Generalization Study of Quantum Neural Network

Generalization is an important feature of neural network, and there have been many studies on it. Recently, with the development of quantum compu-ting, it brings new opportunities. In this paper, we studied a class of quantum neural network constructed by quantum gate. In this model, we mapped the feature data to a quantum state in Hilbert space firstly, and then implement unitary evolution on it, in the end, we can get the classification result by im-plement measurement on the quantum state. Since all the operations in quan-tum neural networks are unitary, the parameters constitute a hypersphere of Hilbert space. Compared with traditional neural network, the parameter space is flatter. Therefore, it is not easy to fall into local optimum, which means the quantum neural networks have better generalization. In order to validate our proposal, we evaluated our model on three public datasets, the results demonstrated that our model has better generalization than the classical neu-ral network with the same structure.

quant-ph↗

arXiv2024

Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning

Dataset pruning aims to construct a coreset capable of achieving performance comparable to the original, full dataset. Most existing dataset pruning methods rely on snapshot-based criteria to identify representative samples, often resulting in poor generalization across various pruning and cross-architecture scenarios. Recent studies have addressed this issue by expanding the scope of training dynamics considered, including factors such as forgetting event and probability change, typically using an averaging approach. However, these works struggle to integrate a broader range of training dynamics without overlooking well-generalized samples, which may not be sufficiently highlighted in an averaging manner. In this study, we propose a novel dataset pruning method termed as Temporal Dual-Depth Scoring (TDDS), to tackle this problem. TDDS utilizes a dual-depth strategy to achieve a balance between incorporating extensive training dynamics and identifying representative samples for dataset pruning. In the first depth, we estimate the series of each sample's individual contributions spanning the training progress, ensuring comprehensive integration of training dynamics. In the second depth, we focus on the variability of the sample-wise contributions identified in the first depth to highlight well-generalized samples. Extensive experiments conducted on CIFAR and ImageNet datasets verify the superiority of TDDS over previous SOTA methods. Specifically on CIFAR-100, our method achieves 54.51% accuracy with only 10% training data, surpassing random selection by 7.83% and other comparison methods by at least 12.69%.

cs.CV↗

arXiv2024

ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT

Zero-shot information extraction (IE) aims to build IE systems from the unannotated text. It is challenging due to involving little human intervention. Challenging but worthwhile, zero-shot IE reduces the time and effort that data labeling takes. Recent efforts on large language models (LLMs, e.g., GPT-3, ChatGPT) show promising performance on zero-shot settings, thus inspiring us to explore prompt-based methods. In this work, we ask whether strong IE models can be constructed by directly prompting LLMs. Specifically, we transform the zero-shot IE task into a multi-turn question-answering problem with a two-stage framework (ChatIE). With the power of ChatGPT, we extensively evaluate our framework on three IE tasks: entity-relation triple extract, named entity recognition, and event extraction. Empirical results on six datasets across two languages show that ChatIE achieves impressive performance and even surpasses some full-shot models on several datasets (e.g., NYT11-HRL). We believe that our work could shed light on building IE models with limited resources.

cs.CL↗

arXiv2024

From Text to Blueprint: Leveraging Text-to-Image Tools for Floor Plan Creation

Artificial intelligence is revolutionizing architecture through text-to-image synthesis, converting textual descriptions into detailed visual representations. We explore AI-assisted floor plan design, focusing on technical background, practical methods, and future directions. Using tools like, Stable Diffusion, AI leverages models such as Generative Adversarial Networks and Variational Autoencoders to generate complex and functional floorplans designs. We evaluates these AI models' effectiveness in generating residential floor plans from text prompts. Through experiments with reference images, text prompts, and sketches, we assess the strengths and limitations of current text-to-image technology in architectural visualization. Architects can use these AI tools to streamline design processes, create multiple design options, and enhance creativity and collaboration. We highlight AI's potential to drive smarter, more efficient floorplan design, contributing to ongoing discussions on AI integration in the design profession and its future impact.

cs.HC↗