arXiv subjects

Yu Liu

Publications and source records attributed to Yu Liu.

At least 559 records · Page 31Linked to original sources

arXiv2024

Research on the Spatial Data Intelligent Foundation Model

This report focuses on spatial data intelligent large models, delving into the principles, methods, and cutting-edge applications of these models. It provides an in-depth discussion on the definition, development history, current status, and trends of spatial data intelligent large models, as well as the challenges they face. The report systematically elucidates the key technologies of spatial data intelligent large models and their applications in urban environments, aerospace remote sensing, geography, transportation, and other scenarios. Additionally, it summarizes the latest application cases of spatial data intelligent large models in themes such as urban development, multimodal systems, remote sensing, smart transportation, and resource environments. Finally, the report concludes with an overview and outlook on the development prospects of spatial data intelligent large models.

cs.AI↗

arXiv2024

Two infinite families of facets of the holographic entropy cone

We verify that the recently proven infinite families of holographic entropy inequalities are maximally tight, i.e. they are facets of the holographic entropy cone. The proof is technical but it offers some heuristic insight. On star graphs, both families of inequalities quantify how concentrated / spread information is with respect to a dihedral symmetry acting on subsystems. In addition, toric inequalities viewed in the K-basis show an interesting interplay between four-party and six-party perfect tensors.

hep-th↗

arXiv2024

VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models

Large Language Models (LLMs) have training corpora containing large amounts of program code, greatly improving the model's code comprehension and generation capabilities. However, sound comprehensive research on detecting program vulnerabilities, a more specific task related to code, and evaluating the performance of LLMs in this more specialized scenario is still lacking. To address common challenges in vulnerability analysis, our study introduces a new benchmark, VulDetectBench, specifically designed to assess the vulnerability detection capabilities of LLMs. The benchmark comprehensively evaluates LLM's ability to identify, classify, and locate vulnerabilities through five tasks of increasing difficulty. We evaluate the performance of 17 models (both open- and closed-source) and find that while existing models can achieve over 80% accuracy on tasks related to vulnerability identification and classification, they still fall short on specific, more detailed vulnerability analysis tasks, with less than 30% accuracy, making it difficult to provide valuable auxiliary information for professional vulnerability mining. Our benchmark effectively evaluates the capabilities of various LLMs at different levels in the specific task of vulnerability detection, providing a foundation for future research and improvements in this critical area of code security. VulDetectBench is publicly available at https://github.com/Sweetaroo/VulDetectBench.

cs.CR↗

arXiv2024

Multiscale Representation Enhanced Temporal Flow Fusion Model for Long-Term Workload Forecasting

Accurate workload forecasting is critical for efficient resource management in cloud computing systems, enabling effective scheduling and autoscaling. Despite recent advances with transformer-based forecasting models, challenges remain due to the non-stationary, nonlinear characteristics of workload time series and the long-term dependencies. In particular, inconsistent performance between long-term history and near-term forecasts hinders long-range predictions. This paper proposes a novel framework leveraging self-supervised multiscale representation learning to capture both long-term and near-term workload patterns. The long-term history is encoded through multiscale representations while the near-term observations are modeled via temporal flow fusion. These representations of different scales are fused using an attention mechanism and characterized with normalizing flows to handle non-Gaussian/non-linear distributions of time series. Extensive experiments on 9 benchmarks demonstrate superiority over existing methods.

cs.LG↗

arXiv2024

Boundedness of fractional integrals and fractional derivatives on Laguerre Lipschitz spaces

In this paper, we study the boundedness of a class of fractional integrals and derivatives associated with Laguerre polynomial expansions on Laguerre Lipschitz spaces. The consideration of such operators is motivated by the study of corresponding results on Gaussian Lipschitz spaces. The key idea used here is to develop the Poisson integral theory in the Laguerre setting.

math.AP↗

arXiv2024

SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields

The ability to distill object-centric abstractions from intricate visual scenes underpins human-level generalization. Despite the significant progress in object-centric learning methods, learning object-centric representations in the 3D physical world remains a crucial challenge. In this work, we propose SlotLifter, a novel object-centric radiance model addressing scene reconstruction and decomposition jointly via slot-guided feature lifting. Such a design unites object-centric learning representations and image-based rendering methods, offering state-of-the-art performance in scene decomposition and novel-view synthesis on four challenging synthetic and four complex real-world datasets, outperforming existing 3D object-centric learning methods by a large margin. Through extensive ablative studies, we showcase the efficacy of designs in SlotLifter, revealing key insights for potential future directions.

cs.CV↗

arXiv2024

Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection

Zero-shot human-object interaction (HOI) detector is capable of generalizing to HOI categories even not encountered during training. Inspired by the impressive zero-shot capabilities offered by CLIP, latest methods strive to leverage CLIP embeddings for improving zero-shot HOI detection. However, these embedding-based methods train the classifier on seen classes only, inevitably resulting in seen-unseen confusion for the model during inference. Besides, we find that using prompt-tuning and adapters further increases the gap between seen and unseen accuracy. To tackle this challenge, we present the first generation-based model using CLIP for zero-shot HOI detection, coined HOIGen. It allows to unlock the potential of CLIP for feature generation instead of feature extraction only. To achieve it, we develop a CLIP-injected feature generator in accordance with the generation of human, object and union features. Then, we extract realistic features of seen samples and mix them with synthetic features together, allowing the model to train seen and unseen classes jointly. To enrich the HOI scores, we construct a generative prototype bank in a pairwise HOI recognition branch, and a multi-knowledge prototype bank in an image-wise HOI recognition branch, respectively. Extensive experiments on HICO-DET benchmark demonstrate our HOIGen achieves superior performance for both seen and unseen classes under various zero-shot settings, compared with other top-performing methods. Code is available at: https://github.com/soberguo/HOIGen

cs.CV↗

arXiv2024

Contrastive masked auto-encoders based self-supervised hashing for 2D image and 3D point cloud cross-modal retrieval

Implementing cross-modal hashing between 2D images and 3D point-cloud data is a growing concern in real-world retrieval systems. Simply applying existing cross-modal approaches to this new task fails to adequately capture latent multi-modal semantics and effectively bridge the modality gap between 2D and 3D. To address these issues without relying on hand-crafted labels, we propose contrastive masked autoencoders based self-supervised hashing (CMAH) for retrieval between images and point-cloud data. We start by contrasting 2D-3D pairs and explicitly constraining them into a joint Hamming space. This contrastive learning process ensures robust discriminability for the generated hash codes and effectively reduces the modality gap. Moreover, we utilize multi-modal auto-encoders to enhance the model's understanding of multi-modal semantics. By completing the masked image/point-cloud data modeling task, the model is encouraged to capture more localized clues. In addition, the proposed multi-modal fusion block facilitates fine-grained interactions among different modalities. Extensive experiments on three public datasets demonstrate that the proposed CMAH significantly outperforms all baseline methods.

cs.CV↗

arXiv2024

Analysis of Parameterized Quantum Circuits: on The Connection Between Expressibility and Types of Quantum Gates

Expressibility is a crucial factor of a Parameterized Quantum Circuit (PQC). In the context of Variational Quantum Algorithms (VQA) based Quantum Machine Learning (QML), a QML model composed of highly expressible PQC and sufficient number of qubits is theoretically capable of approximating any arbitrary continuous function. While much research has explored the relationship between expressibility and learning performance, as well as the number of layers in PQCs, the connection between expressibility and PQC structure has received comparatively less attention. In this paper, we analyze the connection between expressibility and the types of quantum gates within PQCs using a Gradient Boosting Tree model and SHapley Additive exPlanations (SHAP) values. Our analysis is performed on 1,615 instances of PQC derived from 19 PQC topologies, each with 2-18 qubits and 1-5 layers. The findings of our analysis provide guidance for designing highly expressible PQCs, suggesting the integration of more RX or RY gates while maintaining a careful balance with the number of CNOT gates. Furthermore, our evaluation offers an additional evidence of expressibility saturation, as observed by previous studies.

quant-ph↗

arXiv2024

CHORDination: Evaluating Visual Design Choices in Chord Diagrams for Network Data

Chord diagrams are widely used for visualizing data connectivity and flow between nodes in a network. They are effective for representing complex structures through an intuitive and visually appealing circular layout. While previous work has focused on improving aesthetics and interactivity, the influence of fundamental design elements on user perception and information retrieval remains under-explored. In this study, we explored the three primary components of chord diagram anatomy, namely the nodes, circular outline, and arc connections, in three sequential experiment phases. In phase one, we conducted a controlled experiment (N=90) to find the perceptually and information optimized node widths (narrow, medium, wide) and quantities (low, medium, high). This optimal set of node width and quantity sets the foundation for subsequent evaluations and were kept fixed for consistency. In phase two of the study, we conducted an expert design review for identifying the optimal radial tick marks and color gradients. Then in phase three, we evaluated the perceptual and information retrieval performance of the design choices in a controlled experiment (N=24) by comparing four chord diagram designs (baseline, radial tick marks, arc color gradients, both tick marks and color gradients). Results indicated that node width and quantity significantly affected users' information retrieval performance and subjective ratings, whereas the presence of tick marks predominantly influenced subjective experiences. Based on these findings, we discuss the design implications of these visual elements and offer guidance and recommendations for optimizing chord diagram designs in network visualization tasks.

cs.HC↗

arXiv2024

Quantum state tracking and control of a single molecular ion in a thermal environment

Understanding molecular state evolution is central to many disciplines, including molecular dynamics, precision measurement, and molecule-based quantum technology. Details of the evolution are obscured when observing a statistical ensemble of molecules. Here, we reported real-time observations of thermal radiation-driven transitions between individual states ("jumps") of a single molecule. We reversed these "jumps" through microwave-driven transitions, resulting in a twentyfold improvement in the time the molecule dwells in a chosen state. The measured transition rates showed anisotropy in the thermal environment, pointing to the possibility of using single molecules as in-situ probes for the strengths of ambient fields. Our approaches for state detection and manipulation could apply to a wide range of species, facilitating their uses in fields including quantum science, molecular physics, and ion-neutral chemistry.

physics.atom-ph↗

arXiv2024

Enhancing Morphological Measurements of Cosmic Web with Delaunay Tessellation Field Estimation

The density fields constructed by traditional mass assignment methods are susceptible to irritating discreteness, which hinders morphological measurements of cosmic large-scale structure (LSS) through Minkowski functionals (MFs). For alleviating this issue, fixed-kernel smoothing methods are commonly used in literatures, at the expense of losing substantial structural information. In this work, we propose to measure MFs with Delaunay tessellation field estimation (DTFE) technique, with the goal to maximize extractions of morphological information from sparse tracers. We perform our analyses starting from matter fields and progressively extending to halo fields. At matter field level, we elucidate how discreteness affects the morphological measurements of LSS. Then, by comparing with traditional Gaussian smoothing scheme, we preliminarily showcase the advantages of DTFE for enhancing measurements of MFs from sparse tracers. At halo field level, we first numerically investigate various systematic effects on MFs of DTFE fields, which are induced by finite voxel sizes, halo number densities, halo weightings, and redshift space distortions (RSDs), respectively. Then, we explore the statistical power of MFs measured with DTFE for extracting cosmological information encoded in RSDs. We find that MFs measured with DTFE exhibit improvements by $\sim$ $2$ orders of magnitude in discriminative power for RSD effects and by a factor of $\sim$ $3$-$5$ in constraining power on structure growth rate over the MFs measured with Gaussian smoothing. These findings demonstrate the remarkable enhancements in statistical power of MFs achieved by DTFE, showing enormous application potentials of our method in extracting various key cosmological information from galaxy surveys.

astro-ph.CO↗

arXiv2024

QVD: Post-training Quantization for Video Diffusion Models

Recently, video diffusion models (VDMs) have garnered significant attention due to their notable advancements in generating coherent and realistic video content. However, processing multiple frame features concurrently, coupled with the considerable model size, results in high latency and extensive memory consumption, hindering their broader application. Post-training quantization (PTQ) is an effective technique to reduce memory footprint and improve computational efficiency. Unlike image diffusion, we observe that the temporal features, which are integrated into all frame features, exhibit pronounced skewness. Furthermore, we investigate significant inter-channel disparities and asymmetries in the activation of video diffusion models, resulting in low coverage of quantization levels by individual channels and increasing the challenge of quantization. To address these issues, we introduce the first PTQ strategy tailored for video diffusion models, dubbed QVD. Specifically, we propose the High Temporal Discriminability Quantization (HTDQ) method, designed for temporal features, which retains the high discriminability of quantized features, providing precise temporal guidance for all video frames. In addition, we present the Scattered Channel Range Integration (SCRI) method which aims to improve the coverage of quantization levels across individual channels. Experimental validations across various models, datasets, and bit-width settings demonstrate the effectiveness of our QVD in terms of diverse metrics. In particular, we achieve near-lossless performance degradation on W8A8, outperforming the current methods by 205.12 in FVD.

cs.CV↗

arXiv2024

Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations

Current deep learning-based low-light image enhancement methods often struggle with high-resolution images, and fail to meet the practical demands of visual perception across diverse and unseen scenarios. In this paper, we introduce a novel approach termed CoLIE, which redefines the enhancement process through mapping the 2D coordinates of an underexposed image to its illumination component, conditioned on local context. We propose a reconstruction of enhanced-light images within the HSV space utilizing an implicit neural function combined with an embedded guided filter, thereby significantly reducing computational overhead. Moreover, we introduce a single image-based training loss function to enhance the model's adaptability to various scenes, further enhancing its practical applicability. Through rigorous evaluations, we analyze the properties of our proposed framework, demonstrating its superiority in both image quality and scene adaptability. Furthermore, our evaluation extends to applications in downstream tasks within low-light scenarios, underscoring the practical utility of CoLIE. The source code is available at https://github.com/ctom2/colie.

cs.CV↗

arXiv2024

MergeNet: Explicit Mesh Reconstruction from Sparse Point Clouds via Edge Prediction

This paper introduces a novel method for reconstructing meshes from sparse point clouds by predicting edge connection. Existing implicit methods usually produce superior smooth and watertight meshes due to the isosurface extraction algorithms~(e.g., Marching Cubes). However, these methods become memory and computationally intensive with increasing resolution. Explicit methods are more efficient by directly forming the face from points. Nevertheless, the challenge of selecting appropriate faces from enormous candidates often leads to undesirable faces and holes. Moreover, the reconstruction performance of both approaches tends to degrade when the point cloud gets sparse. To this end, we propose MEsh Reconstruction via edGE~(MergeNet), which converts mesh reconstruction into local connectivity prediction problems. Specifically, MergeNet learns to extract the features of candidate edges and regress their distances to the underlying surface. Consequently, the predicted distance is utilized to filter out edges that lay on surfaces. Finally, the meshes are reconstructed by refining the triangulations formed by these edges. Extensive experiments on synthetic and real-scanned datasets demonstrate the superiority of MergeNet to SoTA explicit methods.

cs.CV↗

arXiv2024

On the mean $Ψ$-intermediate dimensions

In this paper, we introduce the mean $Ψ$-intermediate dimension which has a value between the mean Hausdorff dimension and the metric mean dimension, and prove the equivalent definition of the mean Hausdorff dimension and the metric mean dimension. Furthermore, we delve into the core properties of the mean $Ψ$-intermediate dimensions. Additionally, we establish the mass distribution principle, a Frostman-type lemma, Hölder distortion, and derive the corresponding product formula. Finally, we provide illustrative examples of the mean $Ψ$-intermediate dimension, demonstrating its practical applications.

math.DS↗

arXiv2024

Technique Report of CVPR 2024 PBDL Challenges

The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches.

cs.CV↗

arXiv2024

Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher

Cross domain object detection learns an object detector for an unlabeled target domain by transferring knowledge from an annotated source domain. Promising results have been achieved via Mean Teacher, however, pseudo labeling which is the bottleneck of mutual learning remains to be further explored. In this study, we find that confidence misalignment of the predictions, including category-level overconfidence, instance-level task confidence inconsistency, and image-level confidence misfocusing, leading to the injection of noisy pseudo label in the training process, will bring suboptimal performance on the target domain. To tackle this issue, we present a novel general framework termed Multi-Granularity Confidence Alignment Mean Teacher (MGCAMT) for cross domain object detection, which alleviates confidence misalignment across category-, instance-, and image-levels simultaneously to obtain high quality pseudo supervision for better teacher-student learning. Specifically, to align confidence with accuracy at category level, we propose Classification Confidence Alignment (CCA) to model category uncertainty based on Evidential Deep Learning (EDL) and filter out the category incorrect labels via an uncertainty-aware selection strategy. Furthermore, to mitigate the instance-level misalignment between classification and localization, we design Task Confidence Alignment (TCA) to enhance the interaction between the two task branches and allow each classification feature to adaptively locate the optimal feature for the regression. Finally, we develop imagery Focusing Confidence Alignment (FCA) adopting another way of pseudo label learning, i.e., we use the original outputs from the Mean Teacher network for supervised learning without label assignment to concentrate on holistic information in the target image. These three procedures benefit from each other from a cooperative learning perspective.

cs.CV↗