Sian Jin
Computer Science · Indiana University
Publications
70
Citations
622
Est. group size
—
Recurring co-author estimate
Active years
8
Publishing since 2019
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.
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
- GFAz: State-of-the-Art Graphical Fragment Assembly Compression
2026
- EmbdC: Error-Bounded Lossy Video Embedding Compression for On-Device LLM Inference
2026
- PackKV: Reducing KV Cache Memory Footprint through LLM-Aware Lossy Compression
arXiv (Cornell University) · 2025
- PackKV: Reducing KV Cache Memory Footprint through LLM-Aware Lossy Compression
arXiv (Cornell University) · 2025
- KVComp: A High-Performance, LLM-Aware, Lossy Compression Framework for KV Cache
arXiv (Cornell University) · 2025
- Accurate Performance Modeling and Uncertainty Analysis of Lossy Compression in Scientific Applications
2025
- Cloud Computing and Big Data Technology
WORLD SCIENTIFIC eBooks · 2025
- Advancing Scientific Data Compression via Cross-Field Prediction
2025
- Beyond End-to-End: Understanding the Limits of LLMs in Scientific Problem Solving
2025
- Accurate Performance Modeling And Uncertainty Analysis of Lossy Compression in Scientific Applications
arXiv (Cornell University) · 2024
- Enhancing Lossy Compression Through Cross-Field Information for Scientific Applications
ArXiv.org · 2024
- NeurLZ: An Online Neural Learning-Based Method to Enhance Scientific Lossy Compression
arXiv (Cornell University) · 2024
- High-performance Effective Scientific Error-bounded Lossy Compression with Auto-tuned Multi-component Interpolation
Proceedings of the ACM on Management of Data · 2024
- GPUFASTQLZ: An Ultra Fast Compression Methodology for Fastq Sequence Data on GPUs
2024
- Enhancing Lossy Compression Through Cross-Field Information for Scientific Applications
2024
- 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