Kyudan Jung

Integrated M.S./Ph.D. at KAIST AI, DAVIAN Lab, advised by Prof. Jaegul Choo. Speech AI Research Intern at Qualcomm AI Research Research focuses on speech and audio language models, full-duplex systems, continuous audio representation, and RL post-training and agentic AI.

resume|email|scholar|github|linkedin|x.com
Kyudan Jung
Career
Apr–Oct 2026
Speech AI Research Intern, Qualcomm AI Research · current
Oct 2025–Apr 2026
WBL Residency, Foundation Research Team, NAVER Cloud
Sep 2025–Present
Integrated M.S. & Ph.D., KAIST AI, DAVIAN Lab · current
Jun–Aug 2025
DL Research Engineer Intern, AI Audio Gen Team, KRAFTON Inc.
Mar 2022–Aug 2025
B.S. Mathematics & Semiconductor, Chung-Ang University — Magna Cum Laude
Publications
speech RL
HiPLEX: Hierarchical Reinforcement Learning for Full Duplex Speech Language Models
Kyudan Jung, Hyunsin Park, Jinhwan Park, Yoonhyung Lee, Jinhyeok Yang, KiHyun Nam, Jinkyu Lee
Under review, ICLR 2027.
speech
Hiding Tool Latency in On-Device Environments with Speech-Conditioned Speculative Execution
Kyudan Jung, Hyunsin Park, Jinhwan Park, Yoonhyung Lee, Jinhyeok Yang, KiHyun Nam, Jinkyu Lee
Under review, ICASSP 2027.
speech
What Survives Temporal Compression? Frequency-Aware Training of Low-Rate Audio Encoders
Kyudan Jung, Sehyun Lee, Song-ha Jo, Jaegul Choo, Sanghyuk Choi
Under review ICASSP 2026
NLP
EditPPT: Faithful Long-Deck Slide Editing via Structured Tool-Using Multi-Agent with Dual-Modal Validators
Jiheon Kim, Kyudan Jung, Jaegul Choo
arXiv
speech NLP
OmniACBench: A Benchmark for Evaluating Context-Grounded Acoustic Control in Omni-Modal Models
Seunghee Kim, Bumkyu Park, Kyudan Jung, Joosung Lee, Soyoon Kim, Jeonghoon Kim, Taeuk Kim, Hwiyeol Jo
EMNLP 2026 Main
paper
speech
SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection
Kyudan Jung*, Jihwan Kim*, Minwoo Lee*, Soyoon Kim, Jeonghoon Kim, Jaegul Choo, Cheonbok Park
arXiv preprint
paper
speech
SOMMELIER: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models
Kyudan Jung, Jihwan Kim, Soyoon Kim, Jeonghoon Kim, Jaegul Choo, Cheonbok Park
ACL 2026 Industry
paper demo code blog
speech
SLICE: Speech Enhancement via Layer-wise Injection of Conditioning Embeddings
Seokhoon Moon, Kyudan Jung, Jaegul Choo
INTERSPEECH 2026
paper
NLP
Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation
Kyudan Jung, Hojun Cho, Jooyeol Yun, Soyoung Yang, Jaehyeok Jang, Jaegul Choo
ACL 2026 Findings
paper code
NLP
HyperCLOVA X 32B Think
NAVER Cloud HyperCLOVA X Team
arXiv 2026
paper
speech NLP
HyperCLOVA X 8B Omni
NAVER Cloud HyperCLOVA X Team
arXiv 2026
paper
other
Fast Fourier Transform-Based Spectral and Temporal Gradient Filtering for Differential Privacy
Hyeju Shin*, Juyoung Yun*, Kyudan Jung*, Seongwon Yun*
CIKM 2025 Human-Centric AI Workshop Oral
paper
show 16 more publications
NLP
Delving into Large Language Models for Effective Time-Series Anomaly Detection
Junwoo Park, Kyudan Jung, Dohyun Lee, Hyuck Lee, Daehoon Gwak, ChaeHun Park, Jaegul Choo, Jaewoong Cho
NeurIPS 2025 ~24.5% accept
paper code
NLP
Enhancing ASR and TTS Models with LLM for Accessible Mathematical Learning
Kyudan Jung*, Sieun Hyeon*, Nam-Joon Kim, Hyun Gon Ryu, Hyuk-Jae Lee
NVIDIA GTC 2025
NLP
TeXBLEU: Automatic Metric for Evaluating LaTeX Format
Kyudan Jung, Nam-Joon Kim, Hyongon Ryu, Sieun Hyeon, Seung-jun Lee, Hyeok-jae Lee
IEEE ICASSP 2025 Oral
paper
NLP
MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula
Sieun Hyeon*, Kyudan Jung*, Jaehee Won, Nam-Joon Kim, Hyun Gon Ryu, Hyuk-Jae Lee, Jaeyoung Do
AAAI 2025 23.4% accept
paper
NLP
MathReader: Text-to-Speech for Mathematical Documents
Sieun Hyeon, Kyudan Jung, Nam-Joon Kim, Hyun Gon Ryu, Jaeyoung Do
IEEE ICASSP 2025 Oral
paper
NLP
MathBridge: A Large Corpus Dataset for Translating Spoken Mathematical Expressions into LaTeX Formulas
Kyudan Jung, Sieun Hyeon, Jeong Youn Kwon, Nam-Joon Kim, Hyun Gon Ryu, Hyuk-Jae Lee, Jaeyoung Do
arXiv preprint
paper
NLP
Analysis of Transformer Decoder Architecture and KV Cache Behavior During LLM Inference
Kyudan Jung, Jeong Youn Kwon, Young-Dae Mun, Byeong-Geun Kang, Joon-seok Song, Min-Ji Kim, Nam-joon Kim, Hyungon Ryu, Hyuk-jae Lee
ICEIC 2025
other
Intuitive Robot Arm Control System based on HMD Hand Tracking
Seung Jun Lee, Tae Hyeong Kim, Hyeong Jin Do, Kyudan Jung, Hyun Gon Ryu, Nam Joon Kim
ICEIC 2025 Oral
other
Enhanced Electrical Performance in SiC Double-Trench MOSFETs through Optimization Techniques
Jae-duck Yoon, Kyudan Jung, Min-ji Kim, Joon-seok Song, Nam-Joon Kim
ICCE Asia 2024
paper
NLP
Analysis and Lineage of the GPT-3 Transformer Decoder Architecture
Kyudan Jung, Jeong Youn Kwon, Young-Dae Mun, Byeong-Geun Kang, Joon-seok Song, Min-Ji Kim, Seung-Jun Lee, Jeongjun Kim, Sung hoon Lee, Sieun Hyeon, Nam-joon Kim, Hyungon Ryu, Hyeonggi Seong, Hyuk-jae Lee
IEIE Fall 2024
paper
other
Semiconductor Photovoltaic Sorting via Weighted Neural Networks (Korean)
Young-Dae Mun, Kyudan Jung, et al.
IEIE Fall 2024
speech
A Whisper-based Approach to Enhancing Multilingual and Code-Switching ASR
Hyeonggi Seong, Jaehee Won, Hyunjun Kim, Kyudan Jung, Sieun Hyun, Namjoon Kim, Hyuk-Jae Lee
IEIE Summer 2024
speech
Analysis about Theoretical Foundations for Method to Enhancing ASR Performance using OCR Word Frequency Differences
Kyudan Jung, Nam-Joon Kim, Hyun Gon Ryu, Hyuk-Jae Lee
IEEE ICCE 2025 Oral
paper
other
Matrix Decomposition and Transformation Techniques for Semiconductors in AI Applications (Korean)
Kyudan Jung, Seungmin Bae, Nam-Joon Kim, Jaepil Lim, Hyun Gon Ryu, Hyuk-Jae Lee
IEIE Summer 2024
paper
speech
Enhancing ASR Performance through Relative Word Frequency in OCR and Normal Word Frequency Analysis
Kyudan Jung, Seungmin Bae, Nam-Joon Kim, Jaepil Lim, Hyun Gon Ryu, Hyuk-Jae Lee
IEEE AICAS 2024 Oral
paper
speech
Improving ASR Performance with OCR Through Using Word Frequency Difference
Kyudan Jung, Seungmin Bae, Nam-Joon Kim, Hyun Gon Ryu, Hyuk-Jae Lee
IEEE ICEIC 2024 Oral
paper
News
Aug 2026 OmniACBench accepted at EMNLP 2026 Main.
Jun 2026 SLICE accepted at INTERSPEECH 2026.
Apr 2026 SOMMELIER accepted at ACL 2026 Industry.
Apr 2026 Talk to Your Slides accepted at ACL 2026 Findings.
Mar 2026 Starting internship at Qualcomm AI Research.
Jan 2026 HyperCLOVA X 8B Omni and HyperCLOVA X 32B Think papers released.
Nov 2025 Grand Prize (2nd overall) at the 1st Korean AI Society AI Frontier Speech Enhancement Challenge.
Oct 2025 Excellence Scholarship for Master's Students.
Oct 2025 Started Residency program at NAVER Cloud.
Sep 2025 Paper accepted at NeurIPS 2025.
Experiences
2026.04 – 2026.10
Research Intern, Qualcomm
Speech AI
2025.10 – 2026.04
Foundation Researcher, NAVER Cloud
WBL Residency program
2025.06 – 2025.08
Deep Learning Research Engineer Intern, KRAFTON, AI Audio Gen Team
advised by Taehong Moon
2025.01 – 2025.08
Undergrad Intern, KAIST AI, DAVIAN Lab
Prof. Jaegul Choo
2024.11 – 2024.12
DRAM Circuit Design Study, CAU
Prof. Donghyeon Han
2023.03 – 2024.11
Undergrad Intern, SNU
Prof. Nam-Joon Kim & Hyungon Ryu (NVIDIA)
2024.06 – 2024.08
Natural Language Processing Study, CAU
Prof. Hwan-hee Lee
2024.06 – 2024.08
Measure Theory Study, CAU
Prof. Young-hoon Hong
2023.06 – 2023.08
Research Intern, Neowine Co., Ltd.
Designed circuit-design lecture materials with LLM
Awards
2025
Grand Prize (2nd overall), AI Frontier Speech Enhancement Challenge
한국인공지능학회 · ₩5,000,000
2025
Excellence Scholarship for Master's Students
석사우수장학금(이공계), ~$1,800/semester × 4 semesters
2024
Chairman's Award, The National Research Foundation of Korea
한국연구재단 이사장상
2024
Kwanjeong Educational Foundation Scholarship
관정이종환재단 19기 학부장학생, ~$17,000
2024
Chung-Ang University Alumni Foundation Scholarship
중앙대학교 총동문회 장학생
2023
Minister of Education Award
교육부 장관상
Academic Services
2026
Program Committee, AAAI 2027
2026
Workshop Reviewer, IEEE SLT 2026
2026
Conference Reviewer, INTERSPEECH 2026
2025
Program Committee, AAAI 2026 Alignment Track
2025
Program Committee, AAAI 2026 Main Track