5 papers
Ask Before It Tells: Benchmark-to-Robot Body-Cue Transfer for a Question-First Bedside Robot
Dongsik Yoon
Body-cue recognition can support assistive robots, but benchmark accuracy does not guarantee reliable behavior under a robot-camera viewpoint. We present Nuni, a bedside robot prot…
CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents
Hyunseok Park, Jihyeon Kim, Jongeun Kim +1
Retrieval-Augmented Generation (RAG) systems lose retrieval accuracy when similar documents coexist in the vector database, causing unnecessary information, hallucinations, and fac…
Resource-Efficient RGB-Only Action Recognition for Edge Deployment
Dongsik Yoon, Jongeun Kim, Dayeon Lee
Resource-constrained assistive monitoring requires compact local video perception and an explicit understanding of how recognition reliability changes under common visual degradati…
From Prompts to Deployment: Auto-Curated Domain-Specific Dataset Generation via Diffusion Models
Dongsik Yoon, Jongeun Kim
In this paper, we present an automated pipeline for generating domain-specific synthetic datasets with diffusion models, addressing the distribution shift between pre-trained model…
Your Super Resolution Model is not Enough for Tackling Real-World Scenarios
Dongsik Yoon, Jongeun Kim
Despite remarkable progress in Single Image Super-Resolution (SISR), traditional models often struggle to generalize across varying scale factors, limiting their real-world applica…