About Me

I am a Member of Technical Staff at FuriosaAI¹, where I lead the AI Research Team. I received my Ph.D. in Electrical and Computer Engineering from Seoul National University, advised by Prof. Nam Ik Cho. Before that, I received my B.S. from the same department.

¹ FuriosaAI closed a $620M Series D at a $2.9B valuation in October 2026. [Blog] [Bloomberg]

News

Sep 2026Two papers (AsyncOPD, EfficientRollout) accepted to NeurIPS 2026.
Aug 2026Received my Ph.D. from Seoul National University.
May 2026Two papers (ReJump, LoSA) accepted to ICML 2026.
Jan 2026Two papers (ParallelBench, Draft-based Approximate Inference) accepted to ICLR 2026.

Projects

OCR System Development with ePopSoft
Developed a pipeline of computer vision models (text detection and recognition) deployed on Furiosa's Gen 1 Vision NPU.
[Blog]

Publications

(* equal contribution, † equal advising)

My research interests are broad, with first-authored publications spanning Machine Learning (NeurIPS, ICML, ICLR), Computer Vision (ECCV, WACV), and Natural Language Processing (COLM, ACL, EACL).
[Blog: ICML 2026] [Blog: ICML & ACL 2025] [Blog: ECCV & COLM 2024]

Preprints

Elicitation or Expansion? Demystifying Gains from Agent Harness Optimization
Younghyun Kim*, Wooseok Seo*, Minseo Kim, Seunghyuk Oh, Minjae Lee, Donghoon Kim, Hyung Il Koo, Jaehyung Kim†, Wonjun Kang†
Under Review Project Page Code

MetaCurate: Evolving Curation Filters for High-Quality Agentic Coding Data
Donghoon Kim*, Seunghyuk Oh*, Kevin Galim, Minseo Kim, Minjae Lee, Younghyun Kim, Wooseok Seo, Hyung Il Koo, Wonjun Kang
Under Review Project Page Code

Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following
Sangyeon Yoon*, Wooseok Seo*, Hamish Ivison, Hyesoo Hong, Donghoon Kim, Wonjun Kang, Albert No†, Jaehyung Kim†
Under Review Code

GEPA-Curator: Curated Learning for Self Improving Agents
Zack Yu*, Nicholas Lee*, Minjae Lee, Lakshya Agarwal, Luca Manolache, Wonjun Kang, Matei Zaharia, Michael W. Mahoney, Kurt Keutzer, Sehoon Kim†, Amir Gholami†
Under Review

2026

AsyncOPD: How Stale Can On-Policy Distillation Be?
Wonjun Kang*, Kevin Galim*, Seunghyuk Oh, Minjun Kang, Sanghyun Park, Donghoon Kim, Minjae Lee, Minseo Kim, Rishabh Tiwari, Yuchen Zeng, Hyung Il Koo, Kangwook Lee
NeurIPS 2026 Code

EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
Minseo Kim*, Minjae Lee*, Seunghyuk Oh, Kevin Galim, Donghoon Kim, Coleman Hooper, Harman Singh, Amir Gholami, Hyung Il Koo, Wonjun Kang
NeurIPS 2026 Code

Characterizing High Bandwidth Flash for LLM Serving
Zack Yu, Chloe Wong, Coleman Hooper, Minjae Lee, Wonjun Kang, Youngjin Cho, Michael W. Mahoney, Yakun Sophia Shao, Kurt Keutzer, Amir Gholami
MICRO 2026 (RAISE-Arch Workshop)

Scaling Test-Time Compute for DLLMs via Parallel Search
Saarth Gaonkar*, Sebastian Zhao*, Minjae Lee*, Coleman Hooper, Wonjun Kang, Michael W. Mahoney, Kurt Keutzer, Chenfeng Xu, Amir Gholami
COLM 2026 (NonAR-LM Workshop)

ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning
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
ICML 2026 Code

LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models
Haocheng Xi, Harman Singh, Yuezhou Hu, Coleman Hooper, Rishabh Tiwari, Aditya Tomar, Minjae Lee, Wonjun Kang, Michael Mahoney, Chenfeng Xu, Kurt Keutzer, Amir Gholami
ICML 2026

ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
Wonjun Kang*, Kevin Galim*, Seunghyuk Oh*, Minjae Lee, Yuchen Zeng, Shuibai Zhang, Coleman Hooper, Yuezhou Hu, Hyung Il Koo, Nam Ik Cho, Kangwook Lee
ICLR 2026 Project Page Code

Draft-based Approximate Inference for LLMs
Kevin Galim*, Ethan Ewer*, Wonjun Kang, Minjae Lee, Hyung Il Koo, Kangwook Lee
ICLR 2026 Code

CATS: Inference-aligned SFT for Diffusion LLMs via Context-sensitivity Aware Trajectory Sampling
Seunghyuk Oh, Minjae Lee, Kevin Galim, Minseo Kim, Hyung Il Koo, Wonjun Kang, Hanbaek Lyu, Kangwook Lee
ICLR 2026 (DeLTa Workshop)

TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs
Minjae Lee*, Wonjun Kang*, Byeongkeun Ahn, Christian Classen, Kevin Galim, Seunghyuk Oh, Minghao Yan, Hyung Il Koo, Kangwook Lee
EACL 2026 (Findings)

2025

State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models
Wonjun Kang*, Kevin Galim*, Yuchen Zeng*, Minjae Lee, Hyung Il Koo, Nam Ik Cho
ACL 2025 (Main) Code

VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
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
ICML 2025 (Oral, Top ~1%) Code

TabFlex: Scaling Tabular Learning to Millions with Linear Attention
Yuchen Zeng*, Tuan Dinh*, Wonjun Kang, Andreas Mueller
ICML 2025 (Spotlight, Top 2.6%) Code

Parameter-Efficient Fine-Tuning of State Space Models
Kevin Galim*, Wonjun Kang*, Yuchen Zeng*, Hyung Il Koo, Kangwook Lee
ICML 2025 (*alphabetical order) Code

Counting Guidance for High Fidelity Text-to-Image Synthesis
Wonjun Kang*, Kevin Galim*, Hyung Il Koo, Nam Ik Cho
WACV 2025 (Oral) Code

In-batch Ensemble Drafting: Robust Speculative Decoding for LVLMs
Minjae Lee*, Wonjun Kang*, Byeongkeun Ahn, Christian Classen, Minghao Yan, Hyung Il Koo, Kangwook Lee
ICLR 2025 (SCOPE Workshop)

UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation
Wonjun Kang, Byeongkeun Ahn, Minjae Lee, Kevin Galim, Seunghyuk Oh, Hyung Il Koo, Nam Ik Cho
IEEE Access Code

Development of OCR Service for Page-Level Recognition for Camera-Captured Document Images
Junyoung Park, Wonjun Kang, Seonji Park, Keuntek Lee, Hyung Il Koo, Nam Ik Cho
IEEE Access

XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization
Aditya Tomar*, Coleman Hooper*, Minjae Lee, Haocheng Xi, Rishabh Tiwari, Wonjun Kang, Luca Manolache, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
Arxiv

2024 and Earlier

Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing
Wonjun Kang*, Kevin Galim*, Hyung Il Koo
ECCV 2024 Code

Can MLLMs Perform Text-to-Image In-Context Learning?
Yuchen Zeng*, Wonjun Kang*, Yicong Chen, Hyung Il Koo, Kangwook Lee
COLM 2024 Code

Face Swapping for Low-Resolution and Occluded Images In-the-Wild
Jaehyun Park, Wonjun Kang, Hyung Il Koo, Nam Ik Cho
IEEE Access

One-Shot Face Reenactment on Megapixels
Wonjun Kang, Geonsu Lee, Hyung Il Koo, Nam Ik Cho
Arxiv

Work Experience

FuriosaAI, June 2021 ~ Present
Member of Technical Staff, AI Research Lead

Education

Seoul National University, Mar 2020 ~ Aug 2026
Ph.D. in Electrical and Computer Engineering

Seoul National University, Mar 2014 ~ Feb 2020 (Military leave: 2.5 years)
B.S. in Electrical and Computer Engineering
GPA: 4.00/4.30 (Summa Cum Laude)

Seoul Science High School, Mar 2011 ~ Feb 2014

Academic Services

Reviewer: NeurIPS, ICML, ICLR, COLM, ACL ARR, AAAI, TMLR