Wonjun Kang

26 papers A* 3A 1Journal 18Unranked 4
YearRankTypeTitle / Venue / Authors
2026 — conf
TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs.
EACL (Findings)
Minjae Lee, Wonjun Kang, Byeongkeun Ahn, Christian Classen, Kevin Galim, Seunghyuk Oh, Minghao Yan, Hyung Il Koo, Kangwook Lee
2026 J jnl
TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs.
CoRR
Minjae Lee, Wonjun Kang, Byeongkeun Ahn, Christian Classen, Kevin Galim, Seunghyuk Oh, Minghao Yan, Hyung Il Koo, Kangwook Lee
2026 J jnl
UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation.
IEEE Access
Wonjun Kang, Byeongkeun Ahn, Minjae Lee, Kevin Galim, Seunghyuk Oh, Hyung Il Koo, Nam Ik Cho
2025 A conf
Counting Guidance for High Fidelity Text-to-Image Synthesis.
WACV
Wonjun Kang, Kevin Galim, Hyung Il Koo, Nam Ik Cho
2025 J jnl
Development of OCR Service for Page-Level Recognition for Camera-Captured Document Images.
IEEE Access
Junyoung Park, Wonjun Kang, Seonji Park, Keuntek Lee, Hyung Il Koo, Nam Ik Cho
2025 J jnl
Draft-based Approximate Inference for LLMs.
CoRR
Kevin Galim, Ethan Ewer, Wonjun Kang, Minjae Lee, Hyung Il Koo, Kangwook Lee
2025 J jnl
ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs.
CoRR
Wonjun Kang, Kevin Galim, Seunghyuk Oh, Minjae Lee, Yuchen Zeng, Shuibai Zhang, Coleman Hooper, Yuezhou Hu, Hyung Il Koo, Nam Ik Cho, Kangwook Lee
2025 A* conf
Parameter-Efficient Fine-Tuning of State Space Models.
ICML
Kevin Galim, Wonjun Kang, Yuchen Zeng, Hyung Il Koo, Kangwook Lee
2025 J jnl
ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning.
CoRR
Yuchen Zeng, Shuibai Zhang, Wonjun Kang, Shutong Wu, Lynnix Zou, Ying Fan, Heeju Kim, Ziqian Lin, Jungtaek Kim, Hyung Il Koo, Dimitris Papailiopoulos, Kangwook Lee
2025 — conf
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models.
ACL (2)
Wonjun Kang, Kevin Galim, Yuchen Zeng, Minjae Lee, Hyung Il Koo, Nam Ik Cho
2025 J jnl
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models.
CoRR
Wonjun Kang, Kevin Galim, Yuchen Zeng, Minjae Lee, Hyung Il Koo, Nam Ik Cho
2025 A* conf
TabFlex: Scaling Tabular Learning to Millions with Linear Attention.
ICML
Yuchen Zeng, Tuan Dinh, Wonjun Kang, Andreas C. Mueller
2025 J jnl
TabFlex: Scaling Tabular Learning to Millions with Linear Attention.
CoRR
Yuchen Zeng, Tuan Dinh, Wonjun Kang, Andreas C. Mueller
2025 J jnl
UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation.
CoRR
Wonjun Kang, Byeongkeun Ahn, Minjae Lee, Kevin Galim, Seunghyuk Oh, Hyung Il Koo, Nam Ik Cho
2025 A* conf
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data.
ICML
Thomas Zeng, Shuibai Zhang, Shutong Wu, Christian Classen, Daewon Chae, Ethan Ewer, Minjae Lee, Heeju Kim, Wonjun Kang, Jackson Kunde, Ying Fan, Jungtaek Kim, Hyung Il Koo, Kannan Ramchandran, Dimitris Papailiopoulos, Kangwook Lee
2025 J jnl
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data.
CoRR
Thomas Zeng, Shuibai Zhang, Shutong Wu, Christian Classen, Daewon Chae, Ethan Ewer, Minjae Lee, Heeju Kim, Wonjun Kang, Jackson Kunde, Ying Fan, Jungtaek Kim, Hyung Il Koo, Kannan Ramchandran, Dimitris Papailiopoulos, Kangwook Lee
2025 J jnl
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization.
CoRR
Aditya Tomar, Coleman Hooper, Minjae Lee, Haocheng Xi, Rishabh Tiwari, Wonjun Kang, Luca Manolache, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2024 J jnl
Can MLLMs Perform Text-to-Image In-Context Learning?
CoRR
Yuchen Zeng, Wonjun Kang, Yicong Chen, Hyung Il Koo, Kangwook Lee
2024 — conf
Eta Inversion: Designing an Optimal Eta Function for Diffusion-Based Real Image Editing.
ECCV (14)
Wonjun Kang, Kevin Galim, Hyung Il Koo
2024 J jnl
Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing.
CoRR
Wonjun Kang, Kevin Galim, Hyung Il Koo
2024 J jnl
Face Swapping for Low-Resolution and Occluded Images In-the-Wild.
IEEE Access
Jaehyun Park, Wonjun Kang, Hyung Il Koo, Nam Ik Cho
2024 J jnl
Parameter-Efficient Fine-Tuning of State Space Models.
CoRR
Kevin Galim, Wonjun Kang, Yuchen Zeng, Hyung Il Koo, Kangwook Lee
2023 J jnl
Counting Guidance for High Fidelity Text-to-Image Synthesis.
CoRR
Wonjun Kang, Kevin Galim, Hyung Il Koo
2022 J jnl
One-Shot Face Reenactment on Megapixels.
CoRR
Wonjun Kang, Geonsu Lee, Hyung Il Koo, Nam Ik Cho
2022 J jnl
Stronger memory representation after memory reinstatement during retrieval in the human hippocampus.
NeuroImage
Joonyoung Kang, Wonjun Kang, Sue-Hyun Lee
2019 — conf
Low-Complexity Scene Understanding Network.
ICIAP (1)
Livia Iordache, Vlad Paunescu, Wonjun Kang, Joonhyung Kwon, Andrei Leica, ByeongMoon Jeon