We are the Intelligent System (IntelliSys) Lab at the ECE Department of Stevens Institute of Technology. Our research focuses on bridging artificial intelligence (AI) and emerging system architectures by developing efficient, robust algorithms and advancing intelligent, high-performance computing systems. Supported by multiple NSF grants, as well as funding and credits from AWS, NIH AIM-AHEAD, and the Computing Research Association (CRA), our work spans theory, algorithms, and real-world systems. Explore our projects.


News

06/13/2026 :inbox_tray: Dr. Wang is invited to serve as an Action Editor (AE) for the Transactions on Machine Learning Research (TMLR).
06/12/2026 :trophy: Our project ``AgentBench-ROCm: Benchmarking and Optimizing Agentic LLM Workloads on AMD GPU Clusters’‘ has been selected to be awarded by AMD University Program’s (AUP’s) with AI & HPC Cluster. Kudos to $AMD!
06/09/2026 :inbox_tray: Dr. Wang will serve as the ACM/IEEE SC27 Reproducibility Initiative Co-Chair.
06/08/2026 :trophy: Our project ``Federated Vision-Language-Action Learning for Embodied AI’‘ has been selected to be awarded by NVIDIA Academic Grant Program. Kudos to $NVDA!
05/28/2026 :trophy: Congratulations to Longzhao Gong, our master’s student RA, on receiving the 2026 Outstanding Master’s Student Award in Computer Engineering! Thanks to our supportive SES community, check the video!
More...

Selected Publications

  1. EuroSys
    Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading
    In Proceedings of ACM European Conference on Computer Systems (EuroSys) 2026
  2. ASPLOS
    RainbowCake: Mitigating Cold-starts in Serverless with Layer-wise Container Caching and Sharing
    In Proceedings of the ACM Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2024
  3. ICLR
    Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
    Haomin Zhuang, Mingxian Yu, Hao Wang, Yang Hua, Jian Li, and Xu Yuan
    In Proceedings of the International Conference on Learning Representations (ICLR) 2024
  4. SC
    Stellaris: Staleness-Aware Distributed Reinforcement Learning with Serverless Computing (Best Student Paper Finalist)
    In Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC) 2024

Sponsors