5 papers
Meta-Reflective Evolution Effectively Improves Production AI Systems
Seung Won Wilson Yoo, Chang Zeng, Aditi Somayajula +7
Large Language Model (LLM)-guided evolutionary optimization has successfully improved prompts, programs, and even entire AI systems. Most optimization methods select a candidate fr…
SPACE-LoRA: Allocating Activation-Subspace Protection for Continual Learning
Seunghyun Yoo, Kiseok Kim, Hyeontae Joo +2
This study addresses the catastrophic forgetting problem that occurs when sequentially learning successive tasks using Low-Rank Adaptation (LoRA) from a lifelong learning perspecti…
HALO: Heterogeneous Admission through Localized Obligations for Safe Agentic Execution
Taewoo Park, Kyeonghyun Yoo, Kiseok Kim +2
Recent agentic AI systems may return a heterogeneous response containing notices, requests, handoffs, and actions. Conditions can change before external use, so components from the…
Selective Agentic Recovery for UAV Autonomy with a Persistent Mission Runtime
Taewoo Park, Kyeonghyun Yoo, Seunghyun Yoo +1
Agentic AI can support unmanned aerial vehicle (UAV) autonomy by providing high-level recovery reasoning when local waypoint- or setpoint-based execution encounters blocked passage…
Contrastive Domain Generalization for Cross-Instrument Molecular Identification in Mass Spectrometry
Seunghyun Yoo, Sanghong Kim, Namkyung Yoon +1
Identifying molecules from mass spectrometry (MS) data remains a fundamental challenge due to the semantic gap between physical spectral peaks and underlying chemical structures. E…