Publications

Seongjin Cha*, Gyuwan Kim*, Dongsu Han, Tao Yang, Insu Han (2026). KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem.

Byeongjin Kim, Gyuwan Kim, Seo Yeon Park (2026). PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM Reasoning. ACL 2026.

Gyuwan Kim, Yang Li, Evangelia Spiliopoulou, Jie Ma, William Yang Wang (2025). Detecting Training Data of Large Language Models via Expectation Maximization. EACL 2026.

Paper Code Poster Slides Video

Soyoung Yoon*, Gyuwan Kim*, Gyu-Hwung Cho, Seung-Won Hwang (2025). AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking. NeurIPS 2025.

Paper Code Poster Video

Dongwon Noh*, Donghyeok Koh*, Junghun Yuk*, Gyuwan Kim*, Jaeyong Lee, Kyungtae Lim, Cheoneum Park (2025). ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic Contexts. Findings of EMNLP 2025.

Paper Code Dataset Video

Woosang Lim*, Zekun Li*, Gyuwan Kim*, Sungyoung Ji*, HyeonJung Kim, Kyuri Choi, Jin Hyuk Lim, Kyungpyo Park, William Yang Wang (2025). MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAG.

Soyoung Yoon, Sungjoon Park, Gyuwan Kim, Junhee Cho, Kihyo Park, Gyu Tae Kim, Minjoon Seo, Alice Oh (2023). Towards Standardizing Korean Grammatical Error Correction: Datasets and Annotation. ACL 2023.

Paper Code Video

Gyuwan Kim, Jinhyuk Lee, Barlas Oguz, Wenhan Xiong, Yizhe Zhang, Yashar Mehdad, William Yang Wang (2022). Bridging the Training-Inference Gap for Dense Phrase Retrieval. Findings of EMNLP 2022.

Paper Poster Slides Video

Jungsoo Park*, Gyuwan Kim*, Jaewoo Kang (2022). Consistency Training with Virtual Adversarial Discrete Perturbation. NAACL 2022.

Shira Guskin, Moshe Wasserblat, Ke Ding, Gyuwan Kim (2021). Dynamic-TinyBERT: Boost TinyBERT's Inference Efficiency by Dynamic Sequence Length. ENLSP Workshop @ NeurIPS 2021.

Paper Code Model Poster

Sunyoung Kwon*, Gyuwan Kim*, Byunghan Lee, Jongsik Chun, Sungroh Yoon, Young-Han Kim (2021). NASCUP: Nucleic Acid Sequence Classification by Universal Probability. IEEE Access 2021.

Paper Code Dataset

Soyoung Yoon*, Gyuwan Kim*, Kyumin Park (2021). SSMix: Saliency-based Span Mixup for Text Classification. Findings of ACL 2021.

Gyuwan Kim, Kyunghyun Cho (2021). Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search. ACL 2021.

Paper Code Slides Video

Seongbin Kim*, Gyuwan Kim*, Seongjin Shin, Sangmin Lee (2020). Two-stage Textual Knowledge Distillation for End-to-End Spoken Language Understanding. ICASSP 2021.

Paper Code Poster

Minjeong Kim, Gyuwan Kim, Sang-Woo Lee, Jung-Woo Ha (2020). ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding. ICASSP 2021.

Byeongho Heo*, Sanghyuk Chun*, Seong Joon Oh, Dongyoon Han, Sangdoo Yun, Gyuwan Kim, Youngjung Uh, Jung-Woo Ha (2020). AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights. ICLR 2021.

Paper Code Slides Video

Gyuwan Kim*, Tae-Hwan Jung* (2020). Large Product Key Memory for Pretrained Language Models. Findings of EMNLP 2020.

Paper Code Video

Sungdong Kim, Sohee Yang, Gyuwan Kim, Sang-Woo Lee (2019). Efficient Dialogue State Tracking by Selectively Overwriting Memory. ACL 2020.

Paper Code Video

Gyuwan Kim (2019). Subword Language Model for Query Auto-Completion. EMNLP-IJCNLP 2019.

Hayoon Yi*, Gyuwan Kim*, Jangho Lee, Sunwoo Ahn, Younghan Lee, Sungroh Yoon, Yunheung Paek (2018). Mimicry Resilient Program Behavior Modeling with LSTM based Branch Models. S&P 2018 DLS Workshop.

Jangho Lee, Gyuwan Kim, Jaeyoon Yoo, Changwoo Jung, Minseok Kim, Sungroh Yoon (2016). Training IBM Watson using Automatically Generated Question-Answer Pairs. HICSS 2017.

Gyuwan Kim, Hayoon Yi, Jangho Lee, Yunheung Paek, Sungroh Yoon (2016). LSTM-Based System-Call Language Modelling and Robust Ensemble Method for Designing Host-Based Intrusion Detection System.