Dongchan Kim
RSS FeedComputer Scientist & Applied Scientist
Senior Staff Applied Scientist & AI Systems Researcher with over a decade of track record at NAVER Search US, Amazon Alexa, and Microsoft Cortana. Specializing in large-scale Information Retrieval, Foundation Models & Autonomous Agents, Spoken Language Understanding (SLU), and High-Throughput Distributed Cloud Systems.
Pioneered core technologies in neural skill shortlisting (US Patent 11,568,863 B1), personalized attention for ultra-scale domain classification, and foundational research on Retrieval Collapse and clinical memory architectures published across ACL, NAACL, TheWebConf, and IEEE.
Explore peer-reviewed Publications , read about my background in About , or browse research articles below.
Featured Posts
PIA: A Personal Intelligence Agent Turning Health Conversations into Records and Records into Understanding
Introduces PIA, a personal intelligence agent that solves critical data loss in general LLM conversational memory by transforming medical dialogues into structured clinical records and multi-dimensional longitudinal understanding.
Retrieval Collapses When AI Pollutes the Web
Pioneering empirical study published at TheWebConf (WWW 2026) identifying 'Retrieval Collapse'—an ecosystem-level failure mode where AI-generated web pollution degrades external evidence discovery in RAG pipelines and search engines.
Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding
Published at IEEE SLT 2018. A coupled representation learning framework that models hierarchical inter-dependencies between domains, intents, and slots in spoken dialog systems.
Efficient Large-Scale Neural Domain Classification with Personalized Attention
Published at ACL 2018. A scalable neural architecture incorporating personalized attention for routing utterances across thousands of overlapping domains with 100x training speedup.
Recent Posts
Curated Foundational Resources for Modern Deep Learning
A curated collection of essential textbooks, interactive courses, and foundational papers for mastering modern deep learning and neural architectures.
Skill Shortlister for Natural Language Processing (US Patent 11,568,863)
US Patent 11,568,863 B1 granted to Amazon Technologies. Scalable neural shortlisting architecture that prunes massive skill spaces into candidate shortlists for low-latency voice assistants.
A Scalable Neural Shortlisting-Reranking Approach for Large-Scale Domain Classification in Natural Language Understanding
Published at NAACL 2018. Introduces a two-stage neural shortlisting and reranking approach for ultra large-scale conversational NLU across 1,500+ domains.
Adversarial Adaptation of Synthetic or Stale Data in NLU Systems
Published at ACL 2017. A novel adversarial neural domain adaptation framework that bridges distribution mismatch caused by synthetic and stale training data in NLU systems.
Domain Attention with an Ensemble of Experts in Conversational AI
Published at ACL 2017. An ensemble-of-experts model with domain attention for adapting conversational systems to new domains without full retraining.
Adaptive Data Transmission in the Cloud
Published at IEEE/ACM IWQoS 2013. Introduces Adaptive TCP (ATCP), a lightweight end-host protocol prioritizing latency-sensitive short flows over background bulk traffic in cloud data centers.