Institute of Artificial Intelligence and Future Networks, Beijing Normal University
Edge Intelligence Systems Lab
Making large models and generative AI fast, reliable, and affordable at the edge
We build edge AI systems that coordinate heterogeneous edge devices with the cloud, so that LLMs, diffusion models, and other AI applications run efficiently under tight compute, memory, and bandwidth budgets. Our work spans LLM serving, efficient generative AI, and container scheduling and resource management, published at ICLR, ICML, ACM MM, IEEE TMC, IEEE TSC, and other venues.
Research
The problems we work on →Cloud-Edge Collaborative LLM Serving
Edge devices have limited compute, while cloud models are powerful but distant and costly. We study how to split requests, caches, and computation between cloud and edge to improve the latency, throughput, and quality of LLM services.
End-to-End Acceleration of LLM Applications
Real-world LLM applications are workflows of RAG, agents, and multiple models. We optimize entire workflows end to end on heterogeneous hardware.
Efficient Generative AI
Diffusion models for image and video generation run dozens of denoising steps. We exploit redundancy across steps with feature caching, feature forecasting, and multi-device collaboration to accelerate generation with little quality loss.
Edge Container Scheduling and Resource Management
Edge clusters are resource-constrained and highly dynamic. We study layer-aware container scheduling, migration, and updates, cold-start optimization, and resource overbooking, using deep reinforcement learning and online algorithms.
Efficient Multimodal Inference and Retrieval
Retrieval and question answering over images, text, audio, and video must be accurate, fast, and memory-efficient on edge devices.
Task Scheduling and Optimization in Edge Computing
Our long-standing work covers task offloading and scheduling, service placement, UAV and vehicular edge computing, crowdsourcing, and federated learning, as well as a survey of on-device AI models.
Highlights
All publications →News
All news →- 2026Two papers accepted to ICML 2026, HeraSys and Semantic Cache Distillation.
- 2026Two papers accepted to ACM MM 2026, PrediT and SCOPE. Code is available.
- 2026-02-27BWCache code released: github.com/hsc113/BWCache.
- 2026-01-21BWCache accepted to ICLR 2026.
- 2025Our survey on on-device AI models, Empowering Edge Intelligence, is published in ACM Computing Surveys.
Join Us
We are recruiting postdocs, PhD and master students, research assistants, and undergraduates.