检索结果-内蒙古大学图书馆

GraphSparseNet: a Novel Method for Large Scale Trafffic Flow Prediction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kong, Weiyang Wu, Kaiqi Zhang, Sen Liu, Yubao Sun Yat-Sen University Guangzhou China Sun Yat-Sen University Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Traffic flow forecasting is a critical spatio-temporal data mining task with wide-ranging applications in intelligent route planning and dynamic traffic management. Recent advancements in deep learning, particularly through Graph Neural Networks (GNNs), have significantly enhanced the accuracy of these forecasts by capturing complex spatio-temporal dynamics. However, the scalability of GNNs remains a challenge due to their exponential growth in model complexity with increasing nodes in the graph. Existing methods to address this issue, including sparsification, decomposition, and kernel-based approaches, either do not fully resolve the complexity issue or risk compromising predictive accuracy. This paper introduces GraphSparseNet (GSNet), a novel framework designed to improve both the scalability and accuracy of GNN-based traffic forecasting models. GraphSparseNet is comprised of two core modules: the Feature Extractor and the Relational Compressor. These modules operate with linear time and space complexity, thereby reducing the overall computational complexity of the model to a linear scale. Our extensive experiments on multiple real-world datasets demonstrate that GraphSparseNet not only significantly reduces training time by 3.51x compared to state-of-the-art linear models but also maintains high predictive performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Scalability

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Junjia Yan, Pengxiang Cai, Jinhang Liu, Jiyang Wang, Zhao Wang, Yitong Wu, Xinglong Li, Guanbin Sun Yat-sen University China ByteDance Intelligent Creation Peng Cheng Laboratory China Guangdong Key Laboratory of Big Data Analysis and Processing China

Text-driven image generation using diffusion models has recently gained significant attention. To enable more flexible image manipulation and editing, recent research has expanded from single image generation to transparent layer generation and multi-layer compositions. However, existing approaches often fail to provide a thorough exploration of multi-layer structures, leading to inconsistent inter-layer interactions, such as occlusion relationships, spatial layout, and shadowing. In this paper, we introduce DreamLayer, a novel framework that enables coherent text-driven generation of multiple image layers, by explicitly modeling the relationship between transparent foreground and background layers. DreamLayer incorporates three key components, i.e., Context-Aware Cross-Attention (CACA) for global-local information exchange, Layer-Shared Self-Attention (LSSA) for establishing robust inter-layer connections, and Information Retained Harmonization (IRH) for refining fusion details at the latent level. By leveraging a coherent full-image context, DreamLayer builds inter-layer connections through attention mechanisms and applies a harmonization step to achieve seamless layer fusion. To facilitate research in multi-layer generation, we construct a high-quality, diverse multi-layer dataset including 400k samples. Extensive experiments and user studies demonstrate that DreamLayer generates more coherent and well-aligned layers, with broad applicability, including latent-space image editing and image-to-layer decomposition. Copyright © 2025, The Authors. All rights reserved.

关键词： Image fusion

SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wan, Wentao Yang, Zhuojie Chen, Yongcan Luo, Chenglin Wang, Ruilin Cai, Kehao Kang, Nan Lin, Liang Wang, Keze School of Computer Science and Engineering Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing China South China Normal University China

Deductive reasoning is a crucial logical capability that assists us in solving complex problems based on existing knowledge. Although augmented by Chain-of-Thought prompts, Large Language Models (LLMs) might not follow the correct reasoning paths. Enhancing the deductive reasoning abilities of LLMs, and leveraging their extensive built-in knowledge for various reasoning tasks, remains an open question. Attempting to mimic the human deductive reasoning paradigm, we propose a multi-stage Syllogistic-Reasoning Framework of Thought (SR-FoT) that enables LLMs to perform syllogistic deductive reasoning to handle complex knowledge-based reasoning tasks. Our SR-FoT begins by interpreting the question and then uses the interpretation and the original question to propose a suitable major premise. It proceeds by generating and answering minor premise questions in two stages to match the minor premises. Finally, it guides LLMs to use the previously generated major and minor premises to perform syllogistic deductive reasoning to derive the answer to the original question. Extensive and thorough experiments on knowledge-based reasoning tasks have demonstrated the effectiveness and advantages of our SR-FoT. Copyright © 2025, The Authors. All rights reserved.

关键词： Knowledge based systems

Aerial Vision-and-Language Navigation with Grid-based View Selection and Map Construction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Ganlong Li, Guanbin Pan, Jia Yu, Yizhou The University of Hong Kong Hong Kong Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing China Peng Cheng Laboratory China

Aerial Vision-and-Language Navigation (Aerial VLN) aims to obtain an unmanned aerial vehicle agent to navigate aerial 3D environments following human instruction. Compared to ground-based VLN, aerial VLN requires the agent to decide the next action in both horizontal and vertical directions based on the first-person view observations. Previous methods struggle to perform well due to the longer navigation path, more complicated 3D scenes, and the neglect of the interplay between vertical and horizontal actions. In this paper, we propose a novel grid-based view selection framework that formulates aerial VLN action prediction as a grid-based view selection task, incorporating vertical action prediction in a manner that accounts for the coupling with horizontal actions, thereby enabling effective altitude adjustments. We further introduce a grid-based bird’s eye view map for aerial space to fuse the visual information in the navigation history, provide contextual scene information, and mitigate the impact of obstacles. Finally, a cross-modal transformer is adopted to explicitly align the long navigation history with the instruction. We demonstrate the superiority of our method in extensive experiments. Copyright © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Zhongzhan Zhong, Shanshan Zhou, Pan Gao, Shanghua Zitnik, Marinka Lin, Liang Sun Yat-sen University China Singapore Management University Singapore Harvard University United States Guangdong Key Laboratory of Big Data Analysis and Processing and Peng Cheng Laboratory China

Recently, numerous benchmarks have been developed to evaluate the logical reasoning abilities of large language models (LLMs). However, assessing the equally important creative capabilities of LLMs is challenging due to the subjective, diverse, and data-scarce nature of creativity, especially in multimodal scenarios. In this paper, we consider the comprehensive pipeline for evaluating the creativity of multimodal LLMs, with a focus on suitable evaluation platforms and methodologies. First, we find the Oogiri game—a creativity-driven task requiring humor, associative thinking, and the ability to produce unexpected responses to text, images, or both. This game aligns well with the input-output structure of modern multimodal LLMs and benefits from a rich repository of high-quality, human-annotated creative responses, making it an ideal platform for studying LLM creativity. Next, beyond using the Oogiri game for standard evaluations like ranking and selection, we propose LoTbench, an interactive, causality-aware evaluation framework, to further address some intrinsic risks in standard evaluations, such as information leakage and limited interpretability. The proposed LoTbench not only quantifies LLM creativity more effectively but also visualizes the underlying creative thought processes. Our results show that while most LLMs exhibit constrained creativity, the performance gap between LLMs and humans is not insurmountable. Furthermore, we observe a strong correlation between results from the multimodal cognition benchmark MMMU and LoTbench, but only a weak connection with traditional creativity metrics. This suggests that LoTbench better aligns with human cognitive theories, highlighting cognition as a critical foundation in the early stages of creativity and enabling the bridging of diverse concepts. Project Page. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： He, Zijian Ning, Yuwei Qin, Yipeng Wang, Wangrun Yang, Sibei Lin, Liang Li, Guanbin Sun Yat-sen University China Cardiff University United Kingdom ShanghaiTech University China Guangdong Key Laboratory of Big Data Analysis and Processing China Peng Cheng Laboratory China

Virtual Try-On (VTON) is a transformative technology in e-commerce and fashion design, enabling realistic digital visualization of clothing on individuals. In this work, we propose VTON 360, a novel 3D VTON method that addresses the open challenge of achieving high-fidelity VTON that supports any-view rendering. Specifically, we leverage the equivalence between a 3D model and its rendered multi-view 2D images, and reformulate 3D VTON as an extension of 2D VTON that ensures 3D consistent results across multiple views. To achieve this, we extend 2D VTON models to include multi-view garments and clothing-agnostic human body images as input, and propose several novel techniques to enhance them, including: i) a pseudo-3D pose representation using normal maps derived from the SMPL-X 3D human model, ii) a multi-view spatial attention mechanism that models the correlations between features from different viewing angles, and iii) a multi-view CLIP embedding that enhances the garment CLIP features used in 2D VTON with camera information. Extensive experiments on large-scale real datasets and clothing images from e-commerce platforms demonstrate the effectiveness of our approach. Project page: https://***/ VTON360. Copyright © 2025, The Authors. All rights reserved.

关键词： Clothes

UNIGS: UNIFIED LANGUAGE-IMAGE-3D PRETRAINING WITH GAUSSIAN SPLATTING

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Haoyuan Zhou, Yanpeng Tang, Tao Song, Jifei Zeng, Yihan Kampffmeyer, Michael Xu, Hang Liang, Xiaodan Shenzhen campus of Sun Yat-sen University China Huawei Noah’s Ark Lab Canada UiT The Arctic University of Norway Norway Peng Cheng Laboratory China Guangdong Key Laboratory of Big Data Analysis and Processing China

Recent advancements in multi-modal 3D pre-training methods have shown promising efficacy in learning joint representations of text, images, and point clouds. However, adopting point clouds as 3D representation fails to fully capture the intricacies of the 3D world and exhibits a noticeable gap between the discrete points and the dense 2D pixels of images. To tackle this issue, we propose UniGS, integrating 3D Gaussian Splatting (3DGS) into multi-modal pre-training to enhance the 3D representation. We first rely on the 3DGS representation to model the 3D world as a collection of 3D Gaussians with color and opacity, incorporating all the information of the 3D scene while establishing a strong connection with 2D images. Then, to achieve Language-Image-3D pertaining, UniGS starts with a pre-trained vision-language model to establish a shared visual and textual space through extensive real-world image-text pairs. Subsequently, UniGS employs a 3D encoder to align the optimized 3DGS with the Language-Image representations to learn unified multi-modal representations. To facilitate the extraction of global explicit 3D features by the 3D encoder and achieve better cross-modal alignment, we additionally introduce a novel Gaussian-Aware Guidance module that guides the learning of fine-grained representations of the 3D domain. Through extensive experiments across the Objaverse, ABO, MVImgNet and SUN RGBD datasets with zero-shot classification, text-driven retrieval and open-world understanding tasks, we demonstrate the effectiveness of UniGS in learning a more general and stronger aligned multi-modal representation. Specifically, UniGS achieves leading results across different 3D tasks with remarkable improvements over previous SOTA, Uni3D, including on zero-shot classification (+9.36%), text-driven retrieval (+4.3%) and open-world understanding (+7.92%). © 2025, CC BY-NC-SA.

关键词： Visual languages

Solving Multiobjective Combinatorial Optimization via Learning to Improve Method

学校读者我要写书评

暂无评论

IEEE Transactions on Emerging Topics in Computational Intelligence 2025年

作者： Ye, Te Zhang, Zizhen Zhang, Qingfu Chen, Jinbiao Wang, Jiahai Sun Yat-sen University School of Computer Science and Engineering Guangzhou510275 China Sun Yat-sen University Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510275 China City University of Hong Kong Department of Computer Science Kowloon Hong Kong

Recently, neural combinatorial optimization (NCO) methods have been prevailing for solving multiobjective combinatorial optimization problems (MOCOPs). Most NCO methods are based on the "Learning to Construct"(L2C) paradigm, where the trained model(s) can directly generate a set of approximate Pareto optimal solutions. However, these methods still suffer from insufficient proximity and poor diversity towards the true Pareto front. In this paper, following the "Learning to Improve"(L2I) paradigm, we propose weight-related policy network (WRPN), a learning-based improvement method for solving MOCOPs. WRPN is incorporated into multiobjective evolutionary algorithm (MOEA) frameworks to effectively guide the search direction. A shared baseline for proximal policy optimization is presented to reduce variance in model training. A quality enhancement mechanism is designed to further refine the Pareto set during model inference. Computational experiments conducted on two classic MOCOPs, i.e., multiobjective traveling salesman problem and multiobjective vehicle routing problem, indicate that our method achieves remarkable results. Notably, our WRPN module can be easily integrated into various MOEA frameworks such as NSGA-II, MOEA/D and MOGLS, providing versatility and applicability across different problem domains. © 2025 IEEE.

关键词： Deep reinforcement learning

Homophily Induced Contrastive Attributed Graph Clustering

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Chen, Man-Sheng Lai, Pei-Yuan Liao, De-Zhang Wang, Chang-Dong Lai, Jian-Huang Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Guangxi Zhuang Autonomous Region Information Center Guangxi Key Laboratory of Digital Infrastructure Nanning China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China South China Technology Commercialization Center Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China

Attributed graph clustering, aiming to discover the underlying graph structure and partition the graph nodes into several disjoint categories, is a basic task in graph data analysis. Although recent efforts over graph contrastive clustering have achieved decent performances, most of them get accustomed to construct the positive neighbor set by the generated pseudo clustering information, directly ignoring the ready-made neighbor nodes and the underlying semantics of edges in a graph. How to well deal with the graph neighbor-specific information to facilitate the performance of graph contrastive clustering is still a challenging problem. Therefore, in this work, we propose a novel Homophily Induced Contrastive Attributed Graph Clustering (HomoCAGC) method, where the power of homophily is exploited in facilitating the performance of contrastive attributed graph clustering, while the pseudo homophily in a graph is also explored and distinguished. Especially, the node feature as reliable information guidance is used to compute the underlying feature-oriented pair-wise node similarity, based on which the positive node pairs in contrastive regularizer are adjusted for better node representation characterization. According to the refined node representations, a triplet self-supervised clustering objective is well-designed to ensure the output embedding is cluster-oriented, and suitable for the downstream clustering task. Extensive experiments on seven benchmarks are conducted to demonstrate the effectiveness of HomoCAGC. © 1991-2012 IEEE.

关键词： Attributed graph clustering contrastive learning graph homophily self-supervised clustering