3 papers
cs.DC2026
Totoro: An Adaptive and Scalable Edge Federated Learning System
Cheng-Wei Ching, Xin Chen, Taehwan Kim +3
Federated Learning (FL) is an emerging distributed machine learning (ML) technique that enables in-situ model training and inference on decentralized edge devices. We propose Totor…
cs.AI2026
A Policy-Driven Runtime Layer for Agentic LLM Serving
Rui Zhang, Chaeeun Kim, Liting Hu
Multi-agent LLM systems have become the dominant production workload, but the serving stack was not built for them. The agent framework above knows agent identities, role, schemas,…
cs.DB2025
AgileDART: An Agile and Scalable Edge Stream Processing Engine
Cheng-Wei Ching, Xin Chen, Chaeeun Kim +4
Edge applications generate a large influx of sensor data on massive scales, and these massive data streams must be processed shortly to derive actionable intelligence. However, tra…