Research Bridge

Research record

Publications are kept here as technical background. Domain-specific work stays secondary to the broader AI systems profile.

3 entriesData & Applied AIModeling and EvaluationLinked Work
Research-to-System Map

Read research as implementation judgment

Research entries are framed by contribution type, portfolio relevance, and the project decisions they support.

modeling 2026

A Context-Adaptive Gated Embedding Framework for Advanced Clinical Decision-Making

Portfolio relevance
Shows modeling judgment that connects diagnostic context and time-series signals hierarchically instead of treating data surfaces as isolated inputs.
Linked project
Mapping in progress
Data SystemsNLP / LLM
evaluation 2025

Deep Learning based Automatic ICD Coding for Nursing Surveillance of Abdominal Surgery Patients

Portfolio relevance
Supports the portfolio claim that NLP/LLM systems should be judged through domain data structure and error distribution, not only headline accuracy.
Data SystemsNLP / LLM
alignment 2025

Empathetic Dialogue Generation Model Using Reinforcement Learning with AI-Based Feedback

Portfolio relevance
Supports the view that LLM response quality should be treated as an evaluation, reward, and policy-update system rather than a prompt-only outcome.
Linked project
Mapping in progress
NLP / LLM
Research Areas

Research grouped by technical question

Read publications by modeling, evaluation, alignment, and domain judgment before browsing by date.

Modeling 1 items
  • A Context-Adaptive Gated Embedding Framework for Advanced Clinical Decision-Making
Evaluation 1 items
  • Deep Learning based Automatic ICD Coding for Nursing Surveillance of Abdominal Surgery Patients
Alignment 1 items
  • Empathetic Dialogue Generation Model Using Reinforcement Learning with AI-Based Feedback
Journal Paper 2026

Mathematics (submitted)

A Context-Adaptive Gated Embedding Framework for Advanced Clinical Decision-Making

Focus modeling Portfolio relevance

Shows modeling judgment that connects diagnostic context and time-series signals hierarchically instead of treating data surfaces as isolated inputs.

Keywords
Clinical Decision Support SystemAutomated ICD Coding +7
Journal Paper 2025

Journal of The Korea Society of Computer and Information

Deep Learning based Automatic ICD Coding for Nursing Surveillance of Abdominal Surgery Patients

Focus evaluation Portfolio relevance

Supports the portfolio claim that NLP/LLM systems should be judged through domain data structure and error distribution, not only headline accuracy.

Keywords
Medical AINursing Surveillance +7
Conference Paper 2025

Korea Computer Congress (KCC)

Empathetic Dialogue Generation Model Using Reinforcement Learning with AI-Based Feedback

Focus alignment Portfolio relevance

Supports the view that LLM response quality should be treated as an evaluation, reward, and policy-update system rather than a prompt-only outcome.

Keywords
Empathetic DialogueReinforcement Learning +6