PFSVHyeonseop YoonApplied NLP / AI Researcher

Applied NLP · Grounded AI · Seoul

Hyeonseop Yoon

AI Research Engineer at MAUM.AI

I build reliable language systems for real operating environments. My work spans grounded retrieval, query expansion, agent systems, model adaptation, evaluation, and serving—guided by an earlier research background in language, cognition, and neural representation.

Full CV · PDFGitHubHugging FaceORCIDEmail

Research

Publications

Research details →

Engineering

Selected work

All work & evidence →
Case study

Grounded QA for enterprise contact centers

A verified-unit QA design that returns an operator-approved answer or abstains instead of generating unsupported policy text.

The documented held-out evaluation reports hybrid retrieval with query augmentation at approximately R@1 0.881–0.930.

Details →
Public model + evaluation

Korean retrieval embeddings

Two public Korean retrieval encoders with model cards and documented AutoRAG evaluation.

On the documented 720-item, 114-query AutoRAG evaluation, the BGE-M3 variant reports MRR 0.7773 and Hit@10 0.9474.

Details →
Runnable code

VisionCardio

An on-device rPPG research prototype spanning model training, Core ML export, and a SwiftUI application.

With a strict participant split, the documented UBFC validation heart-rate MAE improved from 5.63 to 2.80 bpm after fine-tuning.

Details →

Background

Experience

MAUM.AI

AI Research Engineer · AICC R&D

Research and engineering for production language systems across automotive, insurance, finance, and public-sector domains: retrieval, agent systems, model adaptation, evaluation, and serving.

Seoul National University

Researcher · Cognitive & Systems Neuroscience Laboratory

Analyzed recurrent neural-network models of working memory, sensory encoding, and decision bias; reviewed training dynamics and visualized information flow between units.

Korea University

Researcher · Brain Signal Processing Laboratory

Compared human fMRI representations with language-model embeddings using representational similarity analysis across reasoning and conceptual-metaphor tasks.

Recognition

Selected honors

  • 2023
    Outstanding Poster Award
    Korean Society for Human Brain Mapping · Metaphor in Mind and Machine
  • 2023
    Outstanding Poster Award
    Brain Engineering Society of Korea · Comparative Analysis of Brain and NLP Models for Reasoning Tasks
  • 2022
    Outstanding Research Award
    Korea Software Congress, KIISE · Korean Twitter Bot Detection based on Deep Learning

Community

Academic service

  • 2026
    Reviewer
    Grounding Language Models (GroundLM) Workshop at EMNLP 2026
  • 2026
    Reviewer
    Vision-Language Models for Real-World Deployment (VLM4RWD) Workshop at NeurIPS 2026