Sungjae Lee
Sungjae Lee has 2 papers in our library, in 2022–2026, most of them on Language models & pretraining, Code & programming languages, Efficient models & compression; often with Jungseul Ok, Wei Chen.
OpenAlex · ORCID · h-index 1 · 5 works · 18 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 85 times in our library · ⭐ Paper Stars ranking: #7876
Affiliations
Fields, topics and concepts
📚 Shelves 8The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksComputational Theory and Mathematics · 1 workComputer Vision and Pattern Recognition · 1 workHardware and Architecture · 1 workArtificial Intelligence · 1 workArts and Humanities · 1 workInformation Systems · 1 workLanguage and Linguistics · 1 work
🧭 Topics 3Research subjects and languages the work is about.Efficient models & compression · 1 workLanguage models & pretraining · 1 workCode & programming languages · 1 work
Works by year
2020s
Papers
- LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models (2022 · 103 citations)
When large generative language models produce text token by token, inference is limited mainly by memory traffic rather than arithmetic. - PaT: Planning-after-Trial for Efficient Test-Time Code Generation (2026)
Test-time scaling methods for LLM code generation often plan before trying any code (Planning-before-Trial, PbT). Planners such as FunCoder therefore spend compute decomposing every task, including easy ones a model could solve directly. The authors propose Planning-after-Trial (PaT), which reverses this order.
Co-authors here
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
- International Conference on Learning Representations (ICLR): ICLR 2022
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/sungjae-lee/