5 papers
SkillAlchemy: Open-World Agent Skill Creation
Hengjun Wang, Shuyue Wei, Boyi Liu +2
Agent skills are reusable procedural artifacts that extend language agents with specialized workflows, tool conventions, and domain behaviors at inference time. However, creating r…
MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents
Shuyue Wei, Chang Liu, Zimu Zhou +2
Recently, memory management has become a key infrastructure for LLM-based agents, as it directly affects long-horizon reasoning, personalized responses, and knowledge reuse. Howeve…
Federated Personalization of Early-Exit Networks
Boyi Liu, Zimu Zhou, Cheng Fang +1
Personalized Federated Learning (PFL) excels at tailoring client-specific models, which is particularly critical for decentralized and heterogeneous data environments, yet existing…
Efficient Data Valuation Approximation in Federated Learning: A Sampling-based Approach
Shuyue Wei, Yongxin Tong, Zimu Zhou +2
Federated learning paradigm to utilize datasets across multiple data providers. In FL, cross-silo data providers often hesitate to share their high-quality dataset unless their dat…
Efficient and Private Federated Trajectory Matching
Yuxiang Wang, Yuxiang Zeng, Yi Xu +2
Federated Trajectory Matching (FTM) is gaining increasing importance in big trajectory data analytics, supporting diverse applications such as public health, law enforcement, and e…