LabCompass

Sian Jin

Computer Science · Indiana University

Publications

70

Citations

622

Est. group size

Recurring co-author estimate

Active years

8

Publishing since 2019

Research summary
AI-generated

Sian Jin works on data compression for computing systems, especially techniques that reduce the size of large scientific datasets and machine learning data while keeping error within controlled bounds (called error-bounded lossy compression). Recent work extends these ideas to large language models, for example compressing the memory used during model inference, and often uses GPUs and neural networks to make compression faster and more accurate.

Error-bounded lossy data compressionScientific data storage and compressionCompression for large language modelsNeural network and GPU-accelerated compressionHigh-performance and parallel computing

Publication activity has been steady to growing, rising sharply around 2020-2021 and remaining high in recent years (roughly 13-15 papers per year in 2024-2025).

Generated by claude-opus-4-8 from public bibliographic data · Jul 11, 2026

Publication cadence
Publications per year over the last 10 years — averaging 9.0/year recently
17182019: 2 publications192020: 8 publications202021: 15 publications15212022: 7 publications222023: 8 publications232024: 13 publications242025: 15 publications15252026: 2 publications26
Recent publications
Publishes in
  • arXiv (Cornell University)×23
  • IEEE Transactions on Parallel and Distributed Systems×4
  • ACM Computing Surveys×1
  • Proceedings of the ACM on Management of Data×1
  • 2022 IEEE 38th International Conference on Data Engineering (ICDE)×1

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 11, 2026.

Claim or correct this profile