Hiun Kim (김희언) daily 📝

Hiun Kim is an ML engineer on the Naver Search team, working on machine learning for search models with vision and language technologies. Previously, he was an engineer on the Naver Clova team, where he worked on dialog systems, recommendation models, and generative models for local and e-commerce businesses in the East Asian market. Before that, he was an engineer on Naver’s Platform team, focusing on software engineering for web and serving systems.

He is broadly interested in the topic of 1) machine learned (or symbolic) pattern prediction, 2) and applications of these for varying modalities and human activities (e.g. language, vision, sequences), 3) and leverage it for better information mediation. He is interested in helping cultivate better information as well.

Topics include: Machine learning, Natural language processing, and Information retrieval.

From the practitioner’s point of view, he is interested in the development of information products and energies, and studying better methods of transferring developed information products and energies from the energy source of users to the energy source of providers, starting with related supply and demand development, ranging from the medium of “active” question answering to “passive” content exploration, while also taking public concerns into account.

You can visit my LinkedIn or GitHub.

papers

Here is the list of papers based on some of my work (you can also try Google Scholar):

  1. Hiun Kim, Jisu Jeong, Kyung-Min Kim, Dongjun Lee, Hyun Dong Lee, Dongpil Seo, Jeeseung Han, Dong Wook Park, Ji Ae Heo, Rak Yeong Kim. Intent-based Product Collections for E-commerce using Pretrained Language Models. IEEE International Conference on Data Mining (ICDM) Workshop. 2021. [PDF].
  2. Boseop Kim, HyoungSeok Kim, Sang-Woo Lee, Gichang Lee, Donghyun Kwak, Dong Hyeon Jeon, Sunghyun Park, Sungju Kim, Seonhoon Kim, Dongpil Seo, Heungsub Lee, Minyoung Jeong, Sungjae Lee, Minsub Kim, Suk Hyun Ko, Seokhun Kim, Taeyong Park, Jinuk Kim, Soyoung Kang, Na-Hyeon Ryu, Kang Min Yoo, Minsuk Chang, Soobin Suh, Sookyo In, Jinseong Park, Kyungduk Kim, Hiun Kim, Jisu Jeong, Yong Goo Yeo, Donghoon Ham, Dongju Park, Min Young Lee, Jaewook Kang, Inho Kang, Jung-Woo Ha, Woomyoung Park, Nako Sung. What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers. Empirical Methods in Natural Language Processing (EMNLP). 2021. [PDF].
  3. Seungjae Jung, Young-Jin Park, Jisu Jeong, Kyung-Min Kim, Hiun Kim, Minkyu Kim, Hanock Kwak. Global-Local Item Embedding for Temporal Set Prediction. ACM Recommender Systems (RecSys), Late-Breaking Results. 2021. [PDF].
  4. Hiun Kim, Abbas Ahmad, Jaeyoung Hwang, Hamza Baqa, Franck Le Gall, Miguel Angel Reina Ortega, JaeSeung Song. IoT-TaaS: Towards a Prospective IoT Testing Framework. IEEE Access 2018 (Vol. 6, 15480-15493). 2018. [PDF].
  5. Hiun Kim. Object-orientation for Behavior Modeling and Composition. Korea Conference on Software Engineering (KCSE). 2017.

patents

  1. Hiun Kim, Rakyeong Kim, Jisu Jeong. Method, Computer Device, and Computer Program to Recommend Products to Buy Together. KR Patent 10-2739833 (2024). [WEB].
  2. Jiae Heo, Dongjun Lee, Hiun Kim, Jooho Lee, Hyunah Kim, Dongpil Seo, Hyundong Lee, Jisu Jeong. Method and System for Generating Product Groups based on User's Intent of Search Queries. KR Patent 10-2648300 (2024). [WEB].
  3. Jiae Heo, Dongjun Lee, Hiun Kim, Jooho Lee, Hyunah Kim, Dongpil Seo, Hyundong Lee, Jisu Jeong. Method and System for Providing Special Sales Events based on User's Intent of Search Queries. KR Patent 10-2615815 (2023). [WEB].
  4. Jiae Heo, Dongjun Lee, Hiun Kim, Jooho Lee, Hyunah Kim, Dongpil Seo, Hyundong Lee, Jisu Jeong. 検索クエリのユーザ意図に基づいた商品群生成方法及びシステム. JP Patent 7513656 (JP Patent of KR 10-2648300) (2024). [WEB].
  5. Jiae Heo, Dongjun Lee, Hiun Kim, Jooho Lee, Hyunah Kim, Dongpil Seo, Hyundong Lee, Jisu Jeong. 検索クエリのユーザ意図に基づいた特売イベント生成方法及びシステム. JP Patent 7417877 (JP Patent of KR 10-2615815) (2024). [WEB].