arXiv subjects

Xin Xu

Publications and source records attributed to Xin Xu.

At least 199 records · Page 11Linked to original sources

arXiv2024

ImplicitTerrain: a Continuous Surface Model for Terrain Data Analysis

Digital terrain models (DTMs) are pivotal in remote sensing, cartography, and landscape management, requiring accurate surface representation and topological information restoration. While topology analysis traditionally relies on smooth manifolds, the absence of an easy-to-use continuous surface model for a large terrain results in a preference for discrete meshes. Structural representation based on topology provides a succinct surface description, laying the foundation for many terrain analysis applications. However, on discrete meshes, numerical issues emerge, and complex algorithms are designed to handle them. This paper brings the context of terrain data analysis back to the continuous world and introduces ImplicitTerrain (Project homepage available at https://fengyee.github.io/implicit-terrain/), an implicit neural representation (INR) approach for modeling high-resolution terrain continuously and differentiably. Our comprehensive experiments demonstrate superior surface fitting accuracy, effective topological feature retrieval, and various topographical feature extraction that are implemented over this compact representation in parallel. To our knowledge, ImplicitTerrain pioneers a feasible continuous terrain surface modeling pipeline that provides a new research avenue for our community.

cs.CV↗

arXiv2024

Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View

As Natural Language Processing (NLP) systems are increasingly employed in intricate social environments, a pressing query emerges: Can these NLP systems mirror human-esque collaborative intelligence, in a multi-agent society consisting of multiple large language models (LLMs)? This paper probes the collaboration mechanisms among contemporary NLP systems by melding practical experiments with theoretical insights. We fabricate four unique `societies' comprised of LLM agents, where each agent is characterized by a specific `trait' (easy-going or overconfident) and engages in collaboration with a distinct `thinking pattern' (debate or reflection). Through evaluating these multi-agent societies on three benchmark datasets, we discern that certain collaborative strategies not only outshine previous top-tier approaches, but also optimize efficiency (using fewer API tokens). Moreover, our results further illustrate that LLM agents manifest human-like social behaviors, such as conformity and consensus reaching, mirroring foundational social psychology theories. In conclusion, we integrate insights from social psychology to contextualize the collaboration of LLM agents, inspiring further investigations into the collaboration mechanism for LLMs. We commit to sharing our code and datasets\footnote{\url{https://github.com/zjunlp/MachineSoM}.}, hoping to catalyze further research in this promising avenue.

cs.CL↗

arXiv2024

Density-Guided Dense Pseudo Label Selection For Semi-supervised Oriented Object Detection

Recently, dense pseudo-label, which directly selects pseudo labels from the original output of the teacher model without any complicated post-processing steps, has received considerable attention in semi-supervised object detection (SSOD). However, for the multi-oriented and dense objects that are common in aerial scenes, existing dense pseudo-label selection methods are inefficient because they ignore the significant density difference. Therefore, we propose Density-Guided Dense Pseudo Label Selection (DDPLS) for semi-supervised oriented object detection. In DDPLS, we design a simple but effective adaptive mechanism to guide the selection of dense pseudo labels. Specifically, we propose the Pseudo Density Score (PDS) to estimate the density of potential objects and use this score to select reliable dense pseudo labels. On the DOTA-v1.5 benchmark, the proposed method outperforms previous methods especially when labeled data are scarce. For example, it achieves 49.78 mAP given only 5\% of annotated data, which surpasses previous state-of-the-art method given 10\% of annotated data by 1.15 mAP. Our codes is available at https://github.com/Haru-zt/DDPLS.

cs.CV↗

arXiv2024

Semiquantum private comparison via cavity QED

In this paper, we design the first semiquantum private comparison (SQPC) protocol which is realized via cavity quantum electrodynamics (QED) by making use of the evolution law of atom. With the help of a semi-honest third party (TP), the proposed protocol can compare the equality of private inputs from two semiquantum parties who only have limited quantum capabilities. The proposed protocol uses product states as initial quantum resource and employs none of unitary operations, quantum entanglement swapping operation or delay lines. Security proof turns out that it can defeat both the external attack and the internal attack.

quant-ph↗

arXiv2024

Canonized then Minimized RMSD for Three-Dimensional Structures

Existing molecular canonization algorithms typically operate on one-dimensional (1D) string representations or two-dimensional (2D) connectivity graphs of a molecule and are not able to differentiate equivalent atoms based on three-dimensional (3D) structures. The stereochemical tags on each atom are in fact determined according to established Cahn-Ingold-Prelog (CIP) rules for comparing grades, which can help to further differentiate atoms with similar environment. Therefore, a stereochemical-rule-based canonization algorithm that is capable of assigning canonical indices using 3D structural information is of great value. On top of the Schneider-Sayle-Landrum (SSL) partition-based canonization algorithm, we propose an enhanced canonization algorithm to expand its applicability. The initial index assignment rules are redesigned, so that the obtained canonical indices are compatible with the most of the common CIP Sequence Rules, which greatly eases the stereochemical assignment. Furthermore, a branching tiebreaking step is added to secure an accurate evaluation of the structural difference through the minimized root-mean-square deviation (RMSD) between structures, with an option to include hydrogen atoms or not. Our algorithm is implemented with Python and can efficiently obtain minimized RMSD taking into account of the symmetry of molecular systems , contributing to the fields of drug design, molecular docking, and data analysis of molecular dynamics simulation.

physics.chem-ph↗

arXiv2024

An improved upper bound for planar Turán number of double star $S_{2,5}$

The planar Turán number of a graph $H$, denoted by $ex_{\mathcal{P}}(n,H)$, is the maximum number of edges in an $n$-vertex $H$-free planar graph. Recently, D. Ghosh, et al. initiated the topic of double stars and prove that $ex_{\mathcal{P}}(n,S_{2,5})\leq \frac{20}{7}n$. In this paper, we continue to study this and give a sharp upper bound $ex_{\mathcal{P}}(n,S_{2,5})\leq \frac{19}{7}n-\frac{18}{7}$ for all $n\geq 1$, with equality when $n=12$. This improves Ghosh's result.

math.CO↗

arXiv2024

In-context Learning with Retrieved Demonstrations for Language Models: A Survey

Language models, especially pre-trained large language models, have showcased remarkable abilities as few-shot in-context learners (ICL), adept at adapting to new tasks with just a few demonstrations in the input context. However, the model's ability to perform ICL is sensitive to the choice of the few-shot demonstrations. Instead of using a fixed set of demonstrations, one recent development is to retrieve demonstrations tailored to each input query. The implementation of demonstration retrieval is relatively straightforward, leveraging existing databases and retrieval systems. This not only improves the efficiency and scalability of the learning process but also has been shown to reduce biases inherent in manual example selection. In light of the encouraging results and growing research in ICL with retrieved demonstrations, we conduct an extensive review of studies in this area. In this survey, we discuss and compare different design choices for retrieval models, retrieval training procedures, and inference algorithms.

cs.CL↗

arXiv2024

Deep Learning for Visual Speech Analysis: A Survey

Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment. As a powerful AI strategy, deep learning techniques have extensively promoted the development of visual speech learning. Over the past five years, numerous deep learning based methods have been proposed to address various problems in this area, especially automatic visual speech recognition and generation. To push forward future research on visual speech, this paper aims to present a comprehensive review of recent progress in deep learning methods on visual speech analysis. We cover different aspects of visual speech, including fundamental problems, challenges, benchmark datasets, a taxonomy of existing methods, and state-of-the-art performance. Besides, we also identify gaps in current research and discuss inspiring future research directions.

cs.CV↗

arXiv2024

ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge

To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2022 and launch the ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge. This challenge collects over 100 hours of multi-channel speech data recorded inside a new energy vehicle and 40 hours of noise for data augmentation. Two tracks, including automatic speech recognition (ASR) and automatic speech diarization and recognition (ASDR) are set up, using character error rate (CER) and concatenated minimum permutation character error rate (cpCER) as evaluation metrics, respectively. Overall, the ICMC-ASR Challenge attracts 98 participating teams and receives 53 valid results in both tracks. In the end, first-place team USTCiflytek achieves a CER of 13.16% in the ASR track and a cpCER of 21.48% in the ASDR track, showing an absolute improvement of 13.08% and 51.4% compared to our challenge baseline, respectively.

cs.SD↗

arXiv2024

Linear-Time Graph Neural Networks for Scalable Recommendations

In an era of information explosion, recommender systems are vital tools to deliver personalized recommendations for users. The key of recommender systems is to forecast users' future behaviors based on previous user-item interactions. Due to their strong expressive power of capturing high-order connectivities in user-item interaction data, recent years have witnessed a rising interest in leveraging Graph Neural Networks (GNNs) to boost the prediction performance of recommender systems. Nonetheless, classic Matrix Factorization (MF) and Deep Neural Network (DNN) approaches still play an important role in real-world large-scale recommender systems due to their scalability advantages. Despite the existence of GNN-acceleration solutions, it remains an open question whether GNN-based recommender systems can scale as efficiently as classic MF and DNN methods. In this paper, we propose a Linear-Time Graph Neural Network (LTGNN) to scale up GNN-based recommender systems to achieve comparable scalability as classic MF approaches while maintaining GNNs' powerful expressiveness for superior prediction accuracy. Extensive experiments and ablation studies are presented to validate the effectiveness and scalability of the proposed algorithm. Our implementation based on PyTorch is available.

cs.IR↗

arXiv2024

The Study of Mode Switching behavior of PSR J0614+2229 Using the Parkes Ultra-wideband Receiver Observations

In this paper, we presented a detailed single pulse and polarization study of PSR J0614+2229 based on the archived data observed on 2019 August 15 (MJD 58710) and September 12 (MJD 58738) using the Ultra-wideband Low-frequency Receiver on the Parkes radio telescope. The single-pulse sequences show that this pulsar switches between two emission states, in which the emission of state A occurs earlier than that of state B in pulse longitude. We found that the variation in relative brightness between the two states is related to time and both states follow a simple power law very well. Based on the phase-aligned multi-frequency profiles, we found that there is a significant difference in the distributions of spectral index across the emission regions of the two states. Furthermore, we obtained the emission height evolution for the two emission states and found that, at a fixed frequency, the emission height of state A is higher than that of state B. What is even more interesting is that the emission heights of both states A and B have not changed with frequency. Our results suggest that the mode switching of this pulsar is possibly caused by changes in the emission heights that alter the distributions of spectral index across the emission regions of states A and B resulting in the frequency-dependent behaviors, i.e., intensity and pulse width.

astro-ph.HE↗

arXiv2024

Improving XYG3-type Doubly Hybrid Approximation using Self-Interaction Corrected SCAN Density and Orbitals via the PZ-SIC Framework: the xDH@SCAN(SIC) Approach

XYG3-type doubly hybrid approximations (xDH) have gained a widespread recognition for their accuracy in describing a diverse range of chemical and physical interactions. However, a recent study (J. Phys. Chem. 2021, 12, 800-807) has highlighted the limitation of xDH methods in calculating the dissociation of the NaCl molecule. This issue has been related to the density and orbitals used for evaluating the energy in xDH methods, which are obtained from lower-rung hybrid density functional approximations (DFAs) and display substantial density errors in the dissociation limit. In this work, we systematically investigate the influence of density on several challenging datasets and find that the xDH methods are less sensitive to the density errors compared to semi-local and hybrid DFAs. Furthermore, we demonstrate that the self-interaction corrected SCAN density offers superior accuracy compared to the self-consistent SCAN density and Hartree-Fock (HF) density, as evidenced by the charge analysis on the dissociation of heterodimers, such as NaCl and LiF. Building on these insights, we propose a 5-parameter xDH method using the SCAN density and orbitals corrected by the PZ-SIC scheme. This new xDH@SCAN(SIC) method provides a balanced and accurate description across a wide range of challenging systems.

physics.chem-ph↗

arXiv2024

Degenerate bifurcations of two-fold doubly-connected uniformly rotating vortex patches

In this paper, we obtain families of two-fold doubly-connected uniformly rotating vortex patches of the 2-D incompressible Euler equations emanating from some specific annuli. The main difficulty comes from strong degeneracy of the problem, neither the kernel of linearization is one-dimensional nor the transeversallity condition holds. To this end, we make a detailed analysis on the nonlinear functional and the bifurcation curves are obtained by perturbing real algebraic varieties defined by truncated polynomials. In addition, our result partially answers an problem proposed by Hmidi and Mateu in \cite{Hmidi2016a} (\emph{Adv.Math.302 (2016), 799-850}).

math.AP↗

arXiv2023

Enhancing Optimization Through Innovation: The Multi-Strategy Improved Black Widow Optimization Algorithm (MSBWOA)

This paper introduces a Multi-Strategy Improved Black Widow Optimization Algorithm (MSBWOA), designed to enhance the performance of the standard Black Widow Algorithm (BW) in solving complex optimization problems. The proposed algorithm integrates four key strategies: initializing the population using Tent chaotic mapping to enhance diversity and initial exploratory capability; implementing mutation optimization on the least fit individuals to maintain dynamic population and prevent premature convergence; incorporating a non-linear inertia weight to balance global exploration and local exploitation; and adding a random perturbation strategy to enhance the algorithm's ability to escape local optima. Evaluated through a series of standard test functions, the MSBWOA demonstrates significant performance improvements in various dimensions, particularly in convergence speed and solution quality. Experimental results show that compared to the traditional BW algorithm and other existing optimization methods, the MSBWOA exhibits better stability and efficiency in handling a variety of optimization problems. These findings validate the effectiveness of the proposed strategies and offer a new solution approach for complex optimization challenges.

cs.NE↗

arXiv2023

EPNet: An Efficient Pyramid Network for Enhanced Single-Image Super-Resolution with Reduced Computational Requirements

Single-image super-resolution (SISR) has seen significant advancements through the integration of deep learning. However, the substantial computational and memory requirements of existing methods often limit their practical application. This paper introduces a new Efficient Pyramid Network (EPNet) that harmoniously merges an Edge Split Pyramid Module (ESPM) with a Panoramic Feature Extraction Module (PFEM) to overcome the limitations of existing methods, particularly in terms of computational efficiency. The ESPM applies a pyramid-based channel separation strategy, boosting feature extraction while maintaining computational efficiency. The PFEM, a novel fusion of CNN and Transformer structures, enables the concurrent extraction of local and global features, thereby providing a panoramic view of the image landscape. Our architecture integrates the PFEM in a manner that facilitates the streamlined exchange of feature information and allows for the further refinement of image texture details. Experimental results indicate that our model outperforms existing state-of-the-art methods in image resolution quality, while considerably decreasing computational and memory costs. This research contributes to the ongoing evolution of efficient and practical SISR methodologies, bearing broader implications for the field of computer vision.

cs.CV↗

arXiv2023

Continual Learning through Networks Splitting and Merging with Dreaming-Meta-Weighted Model Fusion

It's challenging to balance the networks stability and plasticity in continual learning scenarios, considering stability suffers from the update of model and plasticity benefits from it. Existing works usually focus more on the stability and restrict the learning plasticity of later tasks to avoid catastrophic forgetting of learned knowledge. Differently, we propose a continual learning method named Split2MetaFusion which can achieve better trade-off by employing a two-stage strategy: splitting and meta-weighted fusion. In this strategy, a slow model with better stability, and a fast model with better plasticity are learned sequentially at the splitting stage. Then stability and plasticity are both kept by fusing the two models in an adaptive manner. Towards this end, we design an optimizer named Task-Preferred Null Space Projector(TPNSP) to the slow learning process for narrowing the fusion gap. To achieve better model fusion, we further design a Dreaming-Meta-Weighted fusion policy for better maintaining the old and new knowledge simultaneously, which doesn't require to use the previous datasets. Experimental results and analysis reported in this work demonstrate the superiority of the proposed method for maintaining networks stability and keeping its plasticity. Our code will be released.

cs.CV↗

arXiv2023

Schema-adaptable Knowledge Graph Construction

Conventional Knowledge Graph Construction (KGC) approaches typically follow the static information extraction paradigm with a closed set of pre-defined schema. As a result, such approaches fall short when applied to dynamic scenarios or domains, whereas a new type of knowledge emerges. This necessitates a system that can handle evolving schema automatically to extract information for KGC. To address this need, we propose a new task called schema-adaptable KGC, which aims to continually extract entity, relation, and event based on a dynamically changing schema graph without re-training. We first split and convert existing datasets based on three principles to build a benchmark, i.e., horizontal schema expansion, vertical schema expansion, and hybrid schema expansion; then investigate the schema-adaptable performance of several well-known approaches such as Text2Event, TANL, UIE and GPT-3.5. We further propose a simple yet effective baseline dubbed \textsc{AdaKGC}, which contains schema-enriched prefix instructor and schema-conditioned dynamic decoding to better handle evolving schema. Comprehensive experimental results illustrate that AdaKGC can outperform baselines but still have room for improvement. We hope the proposed work can deliver benefits to the community. Code and datasets available at https://github.com/zjunlp/AdaKGC.

cs.CL↗

arXiv2023

A Counterexample for the Principal Eigenvalue of An Elliptic Operator with Large Advection

There are numerous studies focusing on the convergence of the principal eigenvalue $λ(s)$ as $s\to+\infty$ corresponding to the elliptic eigenvalue problem \begin{align*} -Δφ(x)-2s\mathbf{v}\cdot\nablaφ(x)+c(x)φ(x)=λ(s)φ(x),\quad x\in Ω, \end{align*} where $Ω$ is a bounded domain and the advection term $\mathbf{v}$ under some certain restrictions. In this paper, we construct an infinitely oscillating gradient advection term $\mathbf{v}=\nabla m(x)\in C^1(Ω)$ such that the principal eigenvalue $λ(s)$ does not converge as $s\to+\infty$. As far as we know, this is the first result that guarantee the non-convergence of the principal eigenvalue.

math.AP↗