检索结果-内蒙古大学图书馆

Parallelizing Multi-objective A* Search

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ahmadi, Saman Sturtevant, Nathan R. Raith, Andrea Harabor, Daniel Jalili, Mahdi School of Engineering RMIT University Australia Department of Computing Science University of Alberta Canada Department of Engineering Science University of Auckland New Zealand Department of Data Science and AI Monash University Australia

The Multi-objective Shortest Path (MOSP) problem is a classic network optimization problem that aims to find all Pareto-optimal paths between two points in a graph with multiple edge costs. Recent studies on multi-objective search with A* (MOA*) have demonstrated superior performance in solving difficult MOSP instances. This paper presents a novel search framework that allows efficient parallelization of MOA* with different objective orders. The framework incorporates a unique upper bounding strategy that helps the search reduce the problem’s dimensionality to one in certain cases. Experimental results demonstrate that the proposed framework can enhance the performance of recent A*-based solutions, with the speed-up proportional to the problem dimension. Copyright © 2025, The Authors. All rights reserved.

关键词： Pareto principle

A comparative study between android phone and TV apps

学校读者我要写书评

暂无评论

Automated Software Engineering 2025年第2期32卷 1-30页

作者： Liu, Yonghui Chen, Xiao Liu, Yue Kong, Pingfan Bissyandé, Tegawendé F. Klein, Jacques Sun, Xiaoyu Li, Li Chen, Chunyang Grundy, John Department of Software Systems and Cybersecurity Monash University Melbourne Australia School of Information and Physical Sciences University of Newcastle Newcastle Australia SnT University of Luxembourg Esch-sur-Alzette Luxembourg The School of Computing Australian National University Canberra Australia School of Software Beihang University Beijing China Department of Computer Science Technical University of Munich Munich Germany Faculty of Data Science City University of Macau China

Smart TVs have surged in popularity, leading developers to create TV versions of mobile apps. Understanding the relationship between TV and mobile apps is key to building consistent, secure, and optimized cross-platform experiences while addressing TV-specific SDK challenges. Despite extensive research on mobile apps, TV apps have been given little attention, leaving the relationship between phone and TV apps unexplored. Our study addresses this gap by compiling an extensive collection of 3445 Android phone/TV app pairs from the Google Play Store, launching the first comparative analysis of its kind. We examined these pairs across multiple dimensions, including non-code elements, code structure, security, and privacy aspects. Our findings reveal that while these app pairs could get identified with the same package names, they deploy different artifacts with varying functionality across platforms. TV apps generally exhibit less complexity in terms of hardware-dependent features and code volume but maintain significant shared resource files and components with their phone versions. Interestingly, some categories of TV apps show similar or even severe security and privacy concerns compared to their mobile counterparts. This research aims to assist developers and researchers in understanding phone-TV app relationships, highlight domain-specific concerns necessitating TV-specific tools, and provide insights for migrating apps from mobile to TV platforms. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Television applications

LazyReview A dataset for Uncovering Lazy Thinking in NLP Peer Reviews

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Purkayastha, Sukannya Li, Zhuang Lauscher, Anne Qu, Lizhen Gurevych, Iryna Technical University of Darmstadt Germany School of Computing Technologies Royal Melbourne Institute of Technology Australia Data Science Group University of Hamburg Germany Department of Data Science & AI Monash University Australia

Peer review is a cornerstone of quality control in scientific publishing. With the increasing workload, the unintended use of ‘quick’ heuristics, referred to as lazy thinking, has emerged as a recurring issue compromising review quality. Automated methods to detect such heuristics can help improve the peer-reviewing process. However, there is limited NLP research on this issue, and no real-world dataset exists to support the development of detection tools. This work introduces LAZYREVIEW, a dataset of peer-review sentences annotated with fine-grained lazy thinking categories. Our analysis reveals that Large Language Models (LLMs) struggle to detect these instances in a zero-shot setting. However, instruction-based finetuning on our dataset significantly boosts performance by 10-20 performance points, highlighting the importance of high-quality training data. Furthermore, a controlled experiment demonstrates that reviews revised with lazy thinking feedback are more comprehensive and actionable than those written without such feedback. We will release our dataset and the enhanced guidelines that can be used to train junior reviewers in the community.1 © 2025, CC BY-SA.

关键词： Damage detection

Multimodal Transformer Models for Turn-taking Prediction: Effects on Conversational Dynamics of Human-Agent Interaction during Cooperative Gameplay

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Bae, Young-Ho Bennett, Casey C. Department of Data Science Hanyang University Seoul Korea Republic of Department of Computing & Digital Media DePaul University ChicagoIL United States

This study investigates multimodal turn-taking prediction within human-agent interactions (HAI), particularly focusing on cooperative gaming environments. It comprises both model development and subsequent user study, aiming to refine our understanding and improve conversational dynamics in spoken dialogue systems (SDSs). For the modeling phase, we introduce a novel transformer-based deep learning (DL) model that simultaneously integrates multiple modalities - text, vision, audio, and contextual in-game data to predict turn-taking events in real-time. Our model employs a Crossmodal Transformer architecture to effectively fuse information from these diverse modalities, enabling more comprehensive turn-taking predictions. The model demonstrates superior performance compared to baseline models, achieving 87.3% accuracy and 83.0% macro F1 score. A human user study was then conducted to empirically evaluate the turn-taking DL model in an interactive scenario with a virtual avatar while playing the game Don’t Starve Together, comparing a control condition without turn-taking prediction (n=20) to an experimental condition with our model deployed (n=40). Both conditions included a mix of English and Korean speakers, since turn-taking cues are known to vary by culture. We then analyzed the interaction quality, examining aspects such as utterance counts, interruption frequency, and participant perceptions of the avatar. Results from the user study suggest that our multi-modal turn-taking model not only enhances the fluidity and naturalness of human-agent conversations, but also maintains a balanced conversational dynamic without significantly altering dialogue frequency. The study provides in-depth insights into the influence of turn-taking abilities on user perceptions and interaction quality, underscoring the potential for more contextually adaptive and responsive conversational agents. This research contributes significantly to the fields of HAI and SDSs by presenting a ro

关键词：

BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Zhixuan Chen, Naipeng Choi, Seonghwa Lee, Sanghoon Lin, Weisi College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical Electronic Engineering Yonsei University Korea Republic of

Time-series forecasting is crucial for numerous real-world applications including weather prediction and financial market modeling. While temporal-domain methods remain prevalent, frequency-domain approaches can effectively capture multi-scale periodic patterns, reduce sequence dependencies, and naturally denoise signals. However, existing approaches typically train model components for all frequencies under a unified training objective, often leading to mismatched learning speeds: high-frequency components converge faster and risk overfitting, while low-frequency components underfit due to insufficient training time. To deal with this challenge, we propose BEAT (Balanced frEquency Adaptive Tuning), a novel framework that dynamically monitors the training status for each frequency and adaptively adjusts their gradient updates. By recognizing convergence, overfitting, or underfitting for each frequency, BEAT dynamically reallocates learning priorities, moderating gradients for rapid learners and increasing those for slower ones, alleviating the tension between competing objectives across frequencies and synchronizing the overall learning process. Extensive experiments on seven real-world datasets demonstrate that BEAT consistently outperforms state-of-the-art approaches. © 2025, CC BY.

关键词： Financial markets

Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Zhixuan Yoon, Hyunse Lee, Sanghoon Lin, Weisi College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical Electronic Engineering Yonsei University Korea Republic of

Amodal segmentation aims to infer the complete shape of occluded objects, even when the occluded region’s appearance is unavailable. However, current amodal segmentation methods lack the capability to interact with users through text input and struggle to understand or reason about implicit and complex purposes. While methods like LISA integrate multi-modal large language models (LLMs) with segmentation for reasoning tasks, they are limited to predicting only visible object regions and face challenges in handling complex occlusion scenarios. To address these limitations, we propose a novel task named amodal reasoning segmentation, aiming to predict the complete amodal shape of occluded objects while providing answers with elaborations based on user text input. We develop a generalizable dataset generation pipeline and introduce a new dataset focusing on daily life scenarios, encompassing diverse real-world occlusions. Furthermore, we present AURA (Amodal Understanding and Reasoning Assistant), a novel model with advanced global and spatial-level designs specifically tailored to handle complex occlusions. Extensive experiments validate AURA’s effectiveness on the proposed dataset. The code, model, and dataset will be publicly released. Copyright © 2025, The Authors. All rights reserved.

关键词： Modeling languages

When Words Outperform Vision: VLMs Can Self-Improve Via Text-Only Training For Human-Centered Decision Making

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hu, Zhe Li, Jing Yin, Yu Department of Computing The Hong Kong Polytechnic University Hong Kong Research Centre for Data Science & Artificial Intelligence Department of Computer and Data Sciences Case Western Reserve University United States

Embodied decision-making is fundamental for AI agents operating in real-world environments. While Visual Language Models (VLMs) have advanced this capability, they still struggle with complex decisions, particularly in human-centered situations that require deep reasoning about human needs and values. In this study, we systematically evaluate open-sourced VLMs on multimodal human-centered decision-making tasks. We find that LLMs receiving only textual descriptions unexpectedly outperform their VLM counterparts of similar scale that process actual images, suggesting that visual alignment may hinder VLM abilities. To address this challenge, we propose a novel text-only training approach with synthesized textual data. This method strengthens VLMs’ language components and transfers the learned abilities to multimodal inference, eliminating the need for expensive image-text paired data. Furthermore, we show that VLMs can achieve substantial performance gains through self-improvement, using training data generated by their LLM counterparts rather than relying on larger teacher models like GPT-4. Our findings establish a more efficient and scalable approach to enhancing VLMs’ human-centered decision-making capabilities, opening new avenues for optimizing VLMs through self-improvement mechanisms. © 2025, CC BY-NC-SA.

关键词： Visual languages

RVISA: Reasoning and Verification for Implicit Sentiment Analysis

学校读者我要写书评

暂无评论

IEEE Transactions on Affective computing 2025年

作者： Lai, Wenna Xie, Haoran Xu, Guandong Li, Qing Hong Kong Polytechnic University Department of Computing Hong Kong Lingnan University School of Data Science Hong Kong University of Technology Sydney School of Computer Science Data Science Institute SydneyNSW2007 Australia Education University of Hong Kong Hong Kong

Under the context of the increasing social demand for fine-grained sentiment analysis (SA), implicit sentiment analysis (ISA) poses a significant challenge owing to the absence of salient cue words in expressions. Thus, reliable reasoning is required to understand how sentiment is evoked, enabling the identification of implicit sentiments. In the era of large language models (LLMs), encoder-decoder (ED) LLMs have emerged as popular backbone models for SA applications, given their impressive text comprehension and reasoning capabilities across diverse tasks. In comparison, decoder-only (DO) LLMs exhibit superior natural language generation and in-context learning capabilities. However, their responses may contain misleading or inaccurate information. To accurately identify implicit sentiments with reliable reasoning, this study introduces a two-stage reasoning framework named Reasoning and Verification for Implicit Sentiment Analysis (RVISA), which leverages the generation ability of DO LLMs and reasoning ability of ED LLMs to train an enhanced reasoner. The framework involves three-hop reasoning prompting to explicitly furnish sentiment elements as cues. The generated rationales are then used to fine-tune an ED LLM into a skilled reasoner. Additionally, we develop a straightforward yet effective answer-based verification mechanism to ensure the reliability of reasoning learning. Evaluation of the proposed method on two benchmark datasets demonstrates that it achieves state-of-the-art performance in ISA. © 2010-2012 IEEE.

关键词： Decoding

Dynamic Distributed Model Compression for Efficient Decentralized Federated Learning and Incentive Provisioning in Edge computing Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Mobile computing 2025年

作者： Asheralieva, Alia Niyato, Dusit Wei, Xuetao Southern University of Science and Technology Department of Computer Science and Engineering 1088 Xueyuan Avenue Shenzhen China Nanyang Technological University College of Computing and Data Science 50 Nanyang Avenue Singapore639798 Singapore

We study decentralized federated learning (DFL) in edge computing networks where edge nodes (ENs) collaboratively train their artificial intelligence (AI) models in a serverless manner without sharing local data. We consider the following critical DFL challenges: i) scarce bandwidth resources of ENs;ii) dynamic, heterogeneous edge environment;iii) incentive provisioning and complex tradeoffs between the DFL performance and training costs. To resolve these challenges, we develop a new model compression method where ENs utilize dynamic, non-identical compression rates to improve the communication efficiency of DFL under time-varying, heterogeneous resource constraints. We show that our method can be formulated as a graphical Markov potential game where ENs act as players deciding on their compression factors and the number of data samples used for model updates. Each EN is incentivized to participate in DFL through rewards based on the EN's contribution to training. We prove that our game has a dominant pure-strategy Nash equilibrium (NE) maximizing its potential function and propose a dynamic distributed compression algorithm in which each EN can find its dominant strategy independently. We show that this algorithm converges to the Pareto-optimal NE, representing the most efficient solution of our game enhancing the DFL performance with minimal costs. © 2002-2012 IEEE.

关键词： Federated learning