Bio

I am a deep learning researcher at KRAFTON.

I received my B.S. degree, M.S. degree, and Ph.D. degree in electrical engineering from KAIST in 2014, 2016, and 2022 respectively, under the supervision of Prof. Changho Suh. 

Research Interests

Information theory, Machine learning 

News

(Jan. 2021) TOP 10 KAIST Research Achievements of 2020 (KAIST Annual R&D Report):

• Fair machine learning (paper, article)

(Aug. 2020) Won the naver paper award 

(2019) Won the outstanding teaching assistant award 

• • EE623: Information Theory (Fall 2019)

Publications

(2025)

• Distilling LLM Agent into Small Models with Retrieval and Code Tools
  Minki Kang, Jongwon Jeong, Seanie Lee, Jaewoong Cho, Sung Ju Hwang
  NeurIPS 2025 (spotlight)

• 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

• FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games
  Jaewoo Ahn, Junseo Kim, Heeseung Yun, Jaehyeon Son, Dongmin Park, Jaewoong Cho, Gunhee Kim
  EMNLP 2025

• Alignment as Distribution Learning: Your Preference Model is Explicitly a Language Model
  Jihun Yun, Juno Kim, Jongho Park, Junhyuck Kim, Jongha Jon Ryu, Jaewoong Cho, Kwang-Sung Jun
  Arxiv (preprint)

• Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
  Dongmin Park, Minkyu Kim, Beongjun Choi, Junhyuck Kim, Keon Lee, Jonghyun Lee, Inkyu Park, Byeong-Uk Lee, Jaeyoung Hwang, Jaewoo Ahn, Ameya S. Mahabaleshwarkar, Bilal Kartal, Pritam Biswas, Yoshi Suhara, Kangwook Lee, Jaewoong Cho
  Arxiv (preprint)

• T1: Tool-integrated Self-verification for Test-time Compute Scaling in Small Language Models
  Minki Kang, Jongwon Jeong, Jaewoong Cho
  Arxiv (preprint)

• Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
  Jaehyeon Kim, Taehong Moon, Keon Lee, Jaewoong Cho
  ICML 2025

• Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
  Junhyuck Kim, Jongho Park, Jaewoong Cho, Dimitris Papailiopoulos
  ICML 2025

• Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance [Github]
  Dongmin Park, Sebin Kim, Taehong Moon, Minkyu Kim, Kangwook Lee, Jaewoong Cho
  ICLR 2025 (spotlight)

• DiTTo-TTS: Efficient and Scalable Zero-Shot Text-to-Speech with Diffusion Transformer  [🔊Demo]
  Keon Lee, Dong Won Kim, Jaehyeon Kim, Jaewoong Cho
  ICLR 2025

• Bridging the Gap between Expert and Language Models: Concept-guided Chess Commentary Generation and Evaluation
  Jaechang Kim, Jinmin Goh, Inseok Hwang, Jaewoong Cho, Jungseul Ok
  NAACL 2025

(2024)

• Task Diversity Shortens the ICL Plateau
  Jaeyeon Kim, Sehyun Kwon, Joo Young Choi, Jongho Park, Jaewoong Cho, Jason D. Lee, Ernest K. Ryu
  TMLR

• Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
  Minki Kang, Sung ju Hwang, Gibbeum Lee, Jaewoong Cho
  NeurIPS 2024

• Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model
  Joo Young Choi, Jaesung R. Park, Inkyu Park, Jaewoong Cho, Albert No, Ernest K. Ryu
  TMLR

• Accelerating Multilingual Language Model for Excessively Tokenized Languages
  Jinmin Hong, Gibbeum Lee, Jaewoong Cho
  ACL 2024

• A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
  Taehong Moon, Moonseok Choi, EungGu Yun, Jongmin Yoon, Gayoung Lee, Jaewoong Cho, Juho Lee
  ICML 2024

• Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
  Jongho Park, Jaeseung Park, Zheyang Xiong, Nayoung Lee, Jaewoong Cho, Samet Oymak, Kangwook Lee, Dimitris Papailiopoulos
  ICML 2024 

• CLAM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech  [🔊Demo]
  Jaehyeon Kim, Keon Lee, Seungjun Chung, Jaewoong Cho
  ICLR 2024

• Image Clustering Conditioned on Text Criteria
  Sehyun Kwon, Jaeseung Park, Minkyu Kim, Jaewoong Cho, Ernest K. Ryu, Kangwook Lee
  ICLR 2024

(2023)

• Mini-Batch Optimization of Contrastive Loss
  Jaewoong Cho*, Kartik Sreenivasan*, Keon Lee, Kyunghoo Mun, Soheun Yi, Jeong-Gwan Lee, Anna Lee, Jy-yong Sohn, Dimitris Papailiopoulos, Kangwook Lee
  TMLR

• Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding
  Seongjun Yang, Gibbeum Lee, Jaewoong Cho, Dimitris Papailiopoulos, and Kangwook Lee
  TMLR

• Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback
  TaeHo Yoon, Kibeom Myoung, Keon Lee, Jaewoong Cho, Albert No, Ernest K. Ryu
  NeurIPS 2023

(2022)

• Equal Experience in Recommender Systems
  Jaewoong Cho, Moonseok Choi, Changho Suh
  Arxiv (preprint)

(2020)

• • A fair classifier using kernel density estimation
    Jaewoong Cho, Gyeongjo Hwang, Changho Suh
    NeurIPS 2020

  • A fair classifier using mutual information
    Jaewoong Cho, Gyeongjo Hwang, Changho Suh
    Proceedings of the IEEE International Symposium on Information Theory

(2019)

• • Wasserstein GAN can Perform PCA
    Jaewoong Cho, Changho Suh
    Proceedings of Allerton Conference on Communication, Control, and Computing

(2018)

• • Two-way interference channel capacity: How to have the cake and eat it too
    Changho Suh, Jaewoong Cho, David Tse
    IEEE Transactions on Information Theory, vol. 64, no. 6

(2017)

• • Two-way interference channel capacity: How to have the cake and eat it too
    Changho Suh, Jaewoong Cho, David Tse
    Proceedings of the IEEE International Symposium on Information Theory

(2016)

• • To feedback or not to feedback
    Changho Suh, David Tse, Jaewoong Cho
    Proceedings of the IEEE International Symposium on Information Theory

Projects

(2025)

• Smart ZOI: co-playable characters in the life simulation game inZOI [news][video]

(2022)

• • Synthesizing AI singing voice of the virtual influencer ANA [official music video link]