isl-logo


We are the Intelligent System (IntelliSys) Lab at the ECE Department of Stevens Institute of Technology. Our research bridges artificial intelligence (AI) and novel system architectures by designing efficient and robust AI algorithms and developing intelligent and high-performance computing systems. Check our roadmap.


News

11/25/2025 :pencil: One paper ``PAT: Accelerating LLM Decoding via Prefix-Aware Attention with Resource Efficient Multi-Tile Kernel’’ has been accepted by ASPLOS 2026.
11/23/2025 :pencil: One paper ``Exploring Diffusion Models’ Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks’’ has been accepted by KDD 2026.
11/19/2025 :flags: We are organizing the Embodied Intelligence Networks (EIN) Workshop at IEEE INFOCOM 2026 in Tokyo, Japan, and we warmly invite you to submit your work.
11/17/2025 :pencil: One papers has been accepted by TPDS. Congratulations to Yifan and Hanfei!
11/07/2025 :pencil: Two papers have been accepted by AAAI’26. Congratulations to Zixun and Hanxi!
More...

Selected Publications

  1. ASPLOS
    RainbowCake: Mitigating Cold-starts in Serverless with Layer-wise Container Caching and Sharing
    Hanfei Yu, Rohan Basu Roy, Christian Fontenot, Devesh Tiwari, Jian Li, Hong Zhang, Hao Wang, and Seung-Jong Park
    In Proceedings of the ACM Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2024
    PDF Code Slides
  2. 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
    PDF Code Poster
  3. SC
    Stellaris: Staleness-Aware Distributed Reinforcement Learning with Serverless Computing (Best Student Paper Finalist)
    Hanfei Yu, Hao Wang, Devesh Tiwari, Jian Li, and Seung-Jong Park
    In Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC) 2024
    PDF Code Slides
  4. EuroSys
    Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading
    Hanfei Yu, Xingqi Cui, Hong Zhang, Hao Wang@Rutgers, and Hao Wang
    Accepted by ACM European Conference on Computer Systems (EuroSys) 2026
    PDF

Sponsors