4 citations
- Nanyang Technological UniversitySG4 papers
- Chinese University of Hong KongHK2 papers
- Jinan UniversityCN2 papers
- National University of SingaporeSG2 papers
- University of OregonUS2 papers
- Beijing Electronic Science and Technology InstituteCN1 paper
- Beijing Information Science & Technology UniversityCN1 paper
- Beijing Institute of TechnologyCN1 paper
- Beijing Zhongke Science and Technology (China)CN1 paper
- China United Network Communications Group (China)CN1 paper
- China XD Group (China)CN1 paper
- City University of Hong KongHK1 paper
18 papers
Towards Scalable Fuzzy PSI via Efficient Fuzzy Matching
Meng Hao, Xinpeng Yang, Hanxiao Chen +5
In this paper, we present scalable fuzzy PSI protocols for general distance, supporting both low- and high-dimensional sets. The core technique is two effic…
AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection
Gou Tan, Zhensu Sun, Jieke Shi +10
Agent systems rely on LLM APIs for every response, but these APIs can return server errors, truncated responses, or corrupted content that propagates through downstream agents and…
Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework
Zhaoqi Wang, Daqing He, Zijian Zhang +13
While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption att…
From Circuits to Hardware: Benchmarking Standard and Qubit-Efficient Quantum Optimization on Real Hardware
Monit Sharma, Hoong Chuin Lau
Despite rapid progress in quantum optimization, broad real-hardware benchmarks comparing multiple algorithmic families across diverse combinatorial problems under a common protocol…
DR-Arena: an Automated Evaluation Framework for Deep Research Agents
Yiwen Gao, Ruochen Zhao, Yang Deng +1
As Large Language Models (LLMs) increasingly operate as Deep Research (DR) Agents capable of autonomous investigation and information synthesis, reliable evaluation of their task p…
LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection
Dezheng Wang, Tong Chen, Guansong Pang +3
As a fundamental data mining task, unsupervised time series anomaly detection (TSAD) aims to build a model for identifying abnormal timestamps without assuming the availability of…