Skip to content
HyScale Lab

Research output

Publications

Peer-reviewed papers and preprints from HyScale Lab and the PI's earlier work.

“There is a time for many words, and there is also a time for sleep.”
— Homer, The Odyssey
Papers
25
Google Scholar citations
1,508
Years
2016–2026
Topics
Pillar
Topic
Other

Showing 25 papers

Work-in-Progress Publications

  1. Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training

    Ruiqi Lai, Dakai An, Wei Gao, Ju Huang, Siran Yang, Jiamang Wang, Lin Qu, Dmitrii Ustiugov, and Wei Wang

    arXiv preprint, 2026

  2. FASER: Fine-Grained Phase Management for Speculative Decoding in Dynamic LLM Serving

    Wenyan Chen, Chengzhi Lu, Yanying Lin, and Dmitrii Ustiugov

    arXiv preprint, 2026

  3. Nexus: Transparent I/O Offloading for High-Density Serverless Computing

    JooYoung Park, Kevin Nguetchouang, Jovan Stojkovic, Likun Zhang, Riccardo Mancini, Marco Cali, and Dmitrii Ustiugov

    arXiv preprint, 2026

  4. SnapShare: Isolation-Preserving Deduplication for Serverless Snapshots

    Leonid Kondrashov, Likun Zhang, André Filipe do Pilar de Jesus, Hans Pistor, Marco Cali, Riccardo Mancini, Rodrigo Bruno, and Dmitrii Ustiugov

    arXiv preprint, 2026

  5. CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference

    Yulin Zou, Yan Chen, Wenyan Chen, JooYoung Park, Shivaraman Nitin, Luo Tao, Francisco Romero, and Dmitrii Ustiugov

    arXiv preprint, 2026

    arXiv2 citations
  6. Melding the Serverless Control Plane with the Conventional Cluster Manager for Speed and Resource Efficiency

    Leonid Kondrashov, Lazar Cvetković, Hancheng Wang, Boxi Zhou, and Dmitrii Ustiugov

    arXiv preprint, 2025

    PDFarXiv6 citations

2026

  1. 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

    arXivCode17 citations
  2. 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

    arXivCode3 citations

2025

  1. 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

    PDFCode17 citations
  2. Manage the Workloads, not the Cluster: Designing a Control Plane for Large-Scale AI Clusters

    Ruiqi Lai, Siyu Cao, Long Li, Long Mai, and Dmitrii Ustiugov

    EuroMLSys, 2025 · Poster

    PDF2 citations
  3. Shattering the Ephemeral Storage Cost Barrier for Data-Intensive Serverless Workflows

    Shyam Jesalpura, Dmitrii Ustiugov, Michal Baczun, Mert Bora Alper, Rustem Feyzkhanov, Edouard Bugnion, Marios Kogias, and Boris Grot

    SESAME, 2025

    PDFCode15 citations

2024

  1. ServerlessLLM: Locality-Enhanced Serverless Inference for Large Language Models

    Yao Fu, Leyang Xue, Yeqi Huang, Andrei-Octavian Brabete, Dmitrii Ustiugov, Yuvraj Patel, and Long Mai

    USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2024

    PDFCode437 citations

2023

  1. Enabling In-Vitro Serverless Systems Research

    Dmitrii Ustiugov, Dohyun Park, Lazar Cvetković, Mihajlo Djokic, Hongyu Hè, Boris Grot, and Ana Klimovic

    Workshop on Resource Disaggregation and Serverless (WORDS) at SOSP, 2023

    PDFCode27 citations

2022

  1. Lukewarm Serverless Functions: Characterization and Optimization

    David Schall, Artemiy Margaritov, Dmitrii Ustiugov, Andreas Sandberg, and Boris Grot

    International Symposium on Computer Architecture (ISCA), 2022

    IEEE Micro Top Picks Honorable Mention 2023

    PDFCode74 citations

2021

  1. Analyzing Tail Latency in Serverless Clouds with STeLLAR

    Dmitrii Ustiugov, Theodor Amariucai, and Boris Grot

    IEEE International Symposium on Workload Characterization (IISWC), 2021

    PDFCodeVideo56 citations
  2. 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

    PDFCodeVideo374 citations
  3. PTEMagnet: Fine-Grained Physical Memory Reservation for Faster Page Walks in Public Clouds

    Artemiy Margaritov, Dmitrii Ustiugov, A Shahab, and Boris Grot

    International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2021

    PDFCodeVideo36 citations

2020

  1. Bankrupt Covert Channel: Turning Network Predictability into Vulnerability

    Dmitrii Ustiugov, Plamen Petrov, M. R. S. Katebzadeh, and Boris Grot

    Workshop on Offensive Technologies (WOOT), 2020

    PDFCode7 citations

2019

  1. Prefetched Address Translation

    Artemiy Margaritov, Dmitrii Ustiugov, Edouard Bugnion, and Boris Grot

    IEEE/ACM International Symposium on Microarchitecture (MICRO), 2019

    PDF117 citations
  2. Mitigating Load Imbalance in Distributed Data Serving with Rack-Scale Memory Pooling

    Stanko Novakovic, Alexandros Daglis, Dmitrii Ustiugov, Edouard Bugnion, Babak Falsafi, and Boris Grot

    ACM Transactions on Computer Systems (TOCS), 2019

    PDF17 citations

2018

  1. Virtual Address Translation via Learned Page Table Indexes

    Artemiy Margaritov, Dmitrii Ustiugov, Edouard Bugnion, and Boris Grot

    NeurIPS Workshop on Machine Learning for Systems, 2018

    PDF23 citations
  2. Design Guidelines for High-Performance SCM Hierarchies

    Dmitrii Ustiugov, Alexandros Daglis, Javier Picorel, Mark Sutherland, Edouard Bugnion, Babak Falsafi, and Dionisios Pnevmatikatos

    International Symposium on Memory Systems (MEMSYS), 2018

    PDF41 citations
  3. Algorithm/Architecture Co-Design for Near-Memory Processing

    Mario Drumond, Alexandros Daglis, Naser Mirzadeh, Dmitrii Ustiugov, Javier Picorel, Babak Falsafi, Boris Grot, and Dionisios Pnevmatikatos

    ACM SIGOPS Operating Systems Review, 2018

    Website7 citations

2017

  1. The Mondrian Data Engine

    Mario Drumond, Alexandros Daglis, Naser Mirzadeh, Dmitrii Ustiugov, Javier Picorel, Babak Falsafi, Boris Grot, and Dionisios Pnevmatikatos

    International Symposium on Computer Architecture (ISCA), 2017

    PDF188 citations

2016

  1. SABRes: Atomic Object Reads for In-Memory Rack-Scale Computing

    Alexandros Daglis, Dmitrii Ustiugov, Stanko Novakovic, Edouard Bugnion, Babak Falsafi, and Boris Grot

    IEEE/ACM International Symposium on Microarchitecture (MICRO), 2016

    PDF31 citations