Jaeseong Lee

23 papers A* 3A 1Journal 8Unranked 11
YearRankTypeTitle / Venue / Authors
2026 — conf
TAGQuant: Token-Aware Clustering for Group-Wise Quantization.
EACL (Industry Track)
Jaeseong Lee, Seung-won Hwang, Aurick Qiao, Zhewei Yao, Yuxiong He
2025 J jnl
Gold-Switch: Training-Free Superposition of Slow- and Fast- Thinking LLMs.
CoRR
Jaeseong Lee, Dayoung Kwon, Seung-won Hwang
2025 J jnl
OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs.
CoRR
Jaeseong Lee, Seung-won Hwang, Aurick Qiao, Gabriele Oliaro, Ye Wang, Samyam Rajbhandari
2025 — conf
PLEX: Adaptive Parameter-Efficient Fine-Tuning for Code LLMs using Lottery-Tickets.
NAACL (Industry Track)
Jaeseong Lee, Hojae Han, Jongyoon Kim, Seung-won Hwang, Naun Kang, KyungJun An, Sungho Jang
2025 — conf
PROM: Pivoted and Regulated Optimization for Multilingual Instruction Learning.
NAACL (Short Papers)
Jaeseong Lee, Seung-won Hwang, Hojin Lee, Yunju Bak, Changmin Lee
2025 — conf
STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning.
ACL (1)
Jaeseong Lee, Seung-won Hwang, Aurick Qiao, Daniel F. Campos, Zhewei Yao, Yuxiong He
2025 — conf
Smarter, Not Harder: Training-Free Adaptive Computation for Transformers.
ACL (Findings)
Romain Storaï, Jaeseong Lee, Seung-won Hwang
2025 J jnl
TALE: Token-Adaptive Low-Rank KVCache Approximation with Reconstruction Elimination.
Trans. Assoc. Comput. Linguistics
Jaeseong Lee, Seung-won Hwang, Aurick Qiao, Daniel F. Campos, Zhewei Yao, Yuxiong He
2024 A* conf
Breaking ReLU Barrier: Generalized MoEfication for Dense Pretrained Models.
EMNLP
Jaeseong Lee, Seung-won Hwang, Wonpyo Park, Mingi Ji
2024 — conf
COMMIT: Code-Mixing English-Centric Large Language Model for Multilingual Instruction Tuning.
NAACL-HLT (Findings)
Jaeseong Lee, Yeonjoon Jung, Seung-won Hwang
2024 — conf
ContrastiveMix: Overcoming Code-Mixing Dilemma in Cross-Lingual Transfer for Information Retrieval.
NAACL (Short Papers)
Junggeun Do, Jaeseong Lee, Seung-won Hwang
2024 A* conf
Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding.
EMNLP
Yeonjoon Jung, Jaeseong Lee, Seungtaek Choi, Dohyeon Lee, Minsoo Kim, Seung-won Hwang
2024 J jnl
Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding.
CoRR
Yeonjoon Jung, Jaeseong Lee, Seungtaek Choi, Dohyeon Lee, Minsoo Kim, Seung-won Hwang
2024 J jnl
STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning.
CoRR
Jaeseong Lee, Seung-won Hwang, Aurick Qiao, Daniel F. Campos, Zhewei Yao, Yuxiong He
2024 — conf
ScriptMix: Mixing Scripts for Low-resource Language Parsing.
NAACL-HLT
Jaeseong Lee, Dohyeon Lee, Seung-won Hwang
2023 — conf
C
ECIR (2)
Jaeseong Lee, Dohyeon Lee, Jongho Kim, Seung-won Hwang
2023 — conf
Multilingual Lottery Tickets to Pretrain Language Models.
EMNLP (Findings)
Jaeseong Lee, Seung-won Hwang
2023 A* conf
Script, Language, and Labels: Overcoming Three Discrepancies for Low-Resource Language Specialization.
AAAI
Jaeseong Lee, Dohyeon Lee, Seung-won Hwang
2022 J jnl
Deep Learning Inference Parallelization on Heterogeneous Processors With TensorRT.
IEEE Embed. Syst. Lett.
Eunjin Jeong, Jangryul Kim, Samnieng Tan, Jaeseong Lee, Soonhoi Ha
2022 — conf
FAD-X: Fusing Adapters for Cross-lingual Transfer to Low-Resource Languages.
AACL/IJCNLP (2)
Jaeseong Lee, Seung-won Hwang, Taesup Kim
2022 J jnl
SNAS: Fast Hardware-Aware Neural Architecture Search Methodology.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.
Jaeseong Lee, Jungsub Rhim, Duseok Kang, Soonhoi Ha
2021 A conf
SCOPA: Soft Code-Switching and Pairwise Alignment for Zero-Shot Cross-lingual Transfer.
CIKM
Dohyeon Lee, Jaeseong Lee, Gyewon Lee, Byung-Gon Chun, Seung-won Hwang
2020 J jnl
S3NAS: Fast NPU-aware Neural Architecture Search Methodology.
CoRR
Jaeseong Lee, Duseok Kang, Soonhoi Ha