· 1 min read
Our new website is under construction
We are rebuilding the HyScale Lab website. Expect things to move around while we work on it.
JooYoung Park
Systems & Cloud Architecture · NTU Singapore
Building the cloud for the AI era.
We study how systems software and computer architecture can make emerging cloud workloads faster, more elastic, and more resource-efficient.
Research pillars
Three directions, one goal: efficient cloud systems.
The HyScale Systems and Cloud Architecture Lab at NTU Singapore builds scalable, efficient cloud systems and open-source research infrastructure.
Serverless cloud systems
Systems for elastic computation and AI inference, built on vHive, our open-source serverless research ecosystem.
vHive · InVitro
LLM and agentic cloud systems
Serving and scaling LLMs and agents, from efficient reasoning to workload-aware AI infrastructure.
ARIES
Multi-modal and Embodied AI cloud systems
An active systems research direction. We will add named artifacts when they are ready to share.
Learn more
- Publications
- 25
- Google Scholar citations
- 1.5K+
- Lab members
- 13
- GitHub stars on our open source
- 416+
Open-source systems
vHive: the serverless research platform used by 30+ universities
Our full-stack open-source environment for representative serverless experimentation, built on AWS Firecracker, containerd and Kubernetes. Its ASPLOS 2021 paper received the Distinguished Artifact Award.
ARIES: an experimentation framework for agent serving systems
Run reproducible agent benchmarks while observing the full trajectory: model calls, harness decisions, stateful tool execution and resource telemetry. Ships with a production trace from Ant Group.
InVitro: realistic serverless load from production traces
A sampler and load generator that turns production traces from Azure, Huawei and IBM into representative invocation traffic for studying serverless clusters. Supports vHive and OpenWhisk.
TokenScale: Timely and Accurate Autoscaling for Disaggregated LLM Serving with Token Velocity
Ruiqi Lai, Hongrui Liu, Chengzhi Lu, Zonghao Liu, Siyu Cao, Siyang Shao, Yixin Zhang, Luo Mai, and Dmitrii Ustiugov
ACM Symposium on Cloud Computing (SoCC), 2026
@inproceedings{lai2026tokenscale, title = {TokenScale: Timely and Accurate Autoscaling for Disaggregated LLM Serving with Token Velocity}, author = {Ruiqi Lai and Hongrui Liu and Chengzhi Lu and Zonghao Liu and Siyu Cao and Siyang Shao and Yixin Zhang and Luo Mai and Dmitrii Ustiugov}, booktitle = {ACM Symposium on Cloud Computing (SoCC)}, year = {2026} }Rethinking AI Cloud Infrastructure for Agentic Serving Systems with the Aries Experimentation Framework
Leonid Kondrashov, Hongrui Liu, JooYoung Park, Boxi Zhou, Zonghao Liu, Chengzhi Lu, Riccardo Mancini, Esha Choukse, Haris Javaid, German Sviridov, Tao Peng, Chen Zhao, Anastasia Avdeeva, Aleksei Gusev, Marios Kogias, Luo Mai, and Dmitrii Ustiugov
ACM Symposium on Cloud Computing (SoCC), 2026
@inproceedings{kondrashov2026rethinkingaicloudinfrastructure, title = {Rethinking AI Cloud Infrastructure for Agentic Serving Systems with the Aries Experimentation Framework}, author = {Leonid Kondrashov and Hongrui Liu and JooYoung Park and Boxi Zhou and Zonghao Liu and Chengzhi Lu and Riccardo Mancini and Esha Choukse and Haris Javaid and German Sviridov and Tao Peng and Chen Zhao and Anastasia Avdeeva and Aleksei Gusev and Marios Kogias and Luo Mai and Dmitrii Ustiugov}, booktitle = {ACM Symposium on Cloud Computing (SoCC)}, year = {2026} }Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency
Colin Hong, Xinyu Guo, Chaanan Anand Singh, Esha Choukse, and Dmitrii Ustiugov
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025 · Oral presentation at the main conference
@inproceedings{hong2025slimsc, title = {{Slim-SC}: Thought Pruning for Efficient Scaling with Self-Consistency}, author = {Hong, Colin and Guo, Xinyu and Singh, Chaanan Anand and Choukse, Esha and Ustiugov, Dmitrii}, booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)}, year = {2025} }Benchmarking, Analysis, and Optimization of Serverless Function Snapshots
Dmitrii Ustiugov, Plamen Petrov, Marios Kogias, Edouard Bugnion, and Boris Grot
International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2021
ASPLOS 2021 Distinguished Artifact Award
@inproceedings{ustiugov2021snapshots, title = {Benchmarking, Analysis, and Optimization of Serverless Function Snapshots}, author = {Ustiugov, Dmitrii and Petrov, Plamen and Kogias, Marios and Bugnion, Edouard and Grot, Boris}, booktitle = {International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)}, year = {2021} }
People
A team across systems, architecture and AI
Postdocs, PhD students, research assistants, interns and undergraduate researchers from around the world work together on open problems in cloud systems.
From the blog
Latest posts
Collaboration & Funding
Working with industry and academia
We thank our past and present collaborators around the globe for their professional and financial support.
Build the next generation of cloud systems with us.
We welcome enquiries from prospective PhD students, postdocs, interns and research assistants interested in serverless, LLM and agentic, and multi-modal AI cloud systems.