7 papers
Skill Description Deception Attack against Task Routing in Internet of Agents
Jiayi He, Xiaofeng Luo, Jiawen Kang +3
A new paradigm, Internet of Agents (IoA), is transforming networked systems into LLM-driven service networks, where heterogeneous agents collaborate through task routing based on t…
Prototype-Regularized Federated Learning for Cross-Domain Aspect Sentiment Triplet Extraction
Zongming Cai, Jianhang Tang, Zhenyong Zhang +3
Aspect Sentiment Triplet Extraction (ASTE) aims to extract all sentiment triplets of aspect terms, opinion terms, and sentiment polarities from a sentence. Existing methods are typ…
LMM-Incentive: Large Multimodal Model-based Incentive Design for User-Generated Content in Web 3.0
Jinbo Wen, Jiawen Kang, Linfeng Zhang +5
Web 3.0 represents the next generation of the Internet, which is widely recognized as a decentralized ecosystem that focuses on value expression and data ownership. By leveraging b…
Inspire or Predict? Exploring New Paradigms in Assisting Classical Planners with Large Language Models
Wenkai Yu, Jianhang Tang, Yang Zhang +4
Addressing large-scale planning problems has become one of the central challenges in the planning community, deriving from the state-space explosion caused by growing objects and a…
HybridRAG-based LLM Agents for Low-Carbon Optimization in Low-Altitude Economy Networks
Jinbo Wen, Cheng Su, Jiawen Kang +5
Low-Altitude Economy Networks (LAENets) are emerging as a promising paradigm to support various low-altitude services through integrated air-ground infrastructure. To satisfy low-l…
Diffusion-based Dynamic Contract for Federated AI Agent Construction in Mobile Metaverses
Jinbo Wen, Jiawen Kang, Yang Zhang +5
Mobile metaverses are envisioned as a transformative digital ecosystem that delivers immersive, intelligent, and ubiquitous services through mobile devices. Driven by Large Languag…
Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss
Jinye Yang, Ji Xu, Di Wu +3
Long-tailed (LT) classification is an unavoidable and challenging problem in the real world. Most existing long-tailed classification methods focus only on solving the class-wise i…