Publications
Peer-reviewed conference papers, workshop proceedings, and preprints.
2026
(2 papers)Jeonghun Yoon, Dongchan Kim, Hongyeon Yu, Young-Bum Kim, Jaegul Choo
arXiv preprint arXiv:2609.31255
A personal intelligence agent solving general LLM memory data loss by turning conversational health dialogue into typed records and longitudinal trajectory understanding.
PaperPDFRead Post & Overview →BibTeX
@article{yoon2026pia, title={PIA: A Personal Intelligence Agent Turning Health Conversations into Records and Records into Understanding}, author={Yoon, Jeonghun and Kim, Dongchan and Yu, Hongyeon and Kim, Young-Bum and Choo, Jaegul}, journal={arXiv preprint arXiv:2609.31255}, year={2026} }Hongyeon Yu, Dongchan Kim, Young-Bum Kim
arXiv preprint arXiv:2602.16136
Empirical study on Retrieval Collapse: how synthetic web content degrades external evidence discovery in RAG pipelines and search engines across two distinct phases (dominance and poisoning).
PaperPDFRead Post & Overview →BibTeX
@article{yu2026retrieval, title={Retrieval Collapses When AI Pollutes the Web}, author={Yu, Hongyeon and Kim, Dongchan and Kim, Young-Bum}, journal={arXiv preprint arXiv:2602.16136}, year={2026} }
2023
(1 paper)Ruhi Sarikaya, Dongchan Kim, Young-Bum Kim
United States Patent US 11,568,863 B1 (Amazon Technologies, Inc.)
Patented systems and methods for low-latency neural skill shortlisting across massive catalogs of voice capabilities in conversational AI assistants.
PaperPDFRead Post & Overview →BibTeX
@misc{sarikaya2023skill, title={Skill shortlister for natural language processing}, author={Sarikaya, Ruhi and Kim, Dongchan and Kim, Young-Bum}, year={2023}, month=jan # "~31", note={US Patent 11,568,863} }
2018
(3 papers)Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding
FeaturedJihwan Lee, Dongchan Kim, Ruhi Sarikaya, Young-Bum Kim
IEEE Spoken Language Technology Workshop (SLT 2018)
A coupled representation learning framework capturing deep inter-dependencies among domain, intent, and slot embeddings in large-scale multi-domain conversational systems.
PaperPDFRead Post & Overview →BibTeX
@inproceedings{lee2018coupled, title={Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding}, author={Lee, Jihwan and Kim, Dongchan and Sarikaya, Ruhi and Kim, Young-Bum}, booktitle={2018 IEEE Spoken Language Technology Workshop (SLT)}, pages={184--191}, year={2018}, organization={IEEE} }Young-Bum Kim, Dongchan Kim, Anjishnu Kumar, Ruhi Sarikaya
Association for Computational Linguistics (ACL 2018)
An efficient personalized attention mechanism for large-scale domain classification across conversational virtual assistants supporting hundreds of domains.
PaperPDFRead Post & Overview →BibTeX
@inproceedings{kim2018efficient, title={Efficient Large-Scale Neural Domain Classification with Personalized Attention}, author={Kim, Young-Bum and Kim, Dongchan and Kumar, Anjishnu and Sarikaya, Ruhi}, booktitle={Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, pages={2214--2224}, year={2018} }Young-Bum Kim, Dongchan Kim, Joo-Kyung Kim, Ruhi Sarikaya
North American Chapter of the Association for Computational Linguistics (NAACL 2018, Industry Track)
A two-stage neural shortlisting-reranking framework meeting ultra-low latency constraints in commercial conversational assistants across hundreds of domains.
PaperPDFRead Post & Overview →BibTeX
@inproceedings{kim2018scalable, title={A Scalable Neural Shortlisting-Reranking Approach for Large-Scale Domain Classification in Natural Language Understanding}, author={Kim, Young-Bum and Kim, Dongchan and Kim, Joo-Kyung and Sarikaya, Ruhi}, booktitle={Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)}, pages={16--24}, year={2018} }
2017
(2 papers)Young-Bum Kim, Karl Stratos, Dongchan Kim
Association for Computational Linguistics (ACL 2017, Short Papers)
An ensemble-of-experts model equipped with domain-level attention to dynamically route utterances and prevent negative transfer across dissimilar conversational domains.
PaperPDFRead Post & Overview →BibTeX
@inproceedings{kim2017domain, title={Domain Attention with an Ensemble of Experts}, author={Kim, Young-Bum and Stratos, Karl and Kim, Dongchan}, booktitle={Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)}, pages={657--662}, year={2017} }Young-Bum Kim, Karl Stratos, Dongchan Kim
Association for Computational Linguistics (ACL 2017, Long Papers)
Adversarial representation learning to adapt out-of-distribution synthetic or legacy training datasets for new NLU conversational domains without overfitting.
PaperPDFRead Post & Overview →BibTeX
@inproceedings{kim2017adversarial, title={Adversarial Adaptation of Synthetic or Stale Data}, author={Kim, Young-Bum and Stratos, Karl and Kim, Dongchan}, booktitle={Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, pages={1297--1307}, year={2017} }
2013
(1 paper)Wenfei Wu, Yizheng Chen, Ramakrishnan Durairajan, Dongchan Kim, Ashok Anand, Aditya Akella
IEEE/ACM International Symposium on Quality of Service (IWQoS 2013)
Adaptive TCP (ATCP): end-host transport modifications prioritizing latency-sensitive short flows over background transfers in cloud data center networks.
PaperPDFRead Post & Overview →BibTeX
@inproceedings{wu2013adaptive, title={Adaptive Data Transmission in the Cloud}, author={Wu, Wenfei and Chen, Yizheng and Durairajan, Ramakrishnan and Kim, Dongchan and Anand, Ashok and Akella, Aditya}, booktitle={2013 IEEE/ACM 21st International Symposium on Quality of Service (IWQoS)}, pages={1--10}, year={2013}, organization={IEEE} }