activity
20242026
collaborators

6 papers

cs.LG2026

EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning

Ahin Lee, Sehyun Yun, Taesik Gong

Mixture-of-Experts (MoE) models scale efficiently but remain costly to adapt due to redundant experts and uniform parameter allocation. Existing parameter-efficient fine-tuning (PE…

cs.CL2026

From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG

Changmin Lee, Jaemin Kim, Taesik Gong

With the rapid emergence of personal AI agents based on Large Language Models (LLMs), implementing them on-device has become essential for privacy and responsiveness. To handle the…

cs.RO2026

Premover: Fast Vision-Language-Action Control by Acting Before Instructions Are Complete

Joonha Park, Jiseung Jeong, Taesik Gong

Vision-Language-Action (VLA) policies are typically evaluated as if the user had finished typing or speaking before the robot begins acting. In real deployment, however, users take…

cs.HC2026

ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues

Yeji Park, Jiwon Tark, Taesik Gong

Large language models (LLMs) are increasingly used by end users, yet existing personalization methods relying on static profiles or text-only signals fail to capture query-specific…

cs.DC2025

Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearables

Taesik Gong, Si Young Jang, Utku Günay Acer +2

The advent of tiny artificial intelligence (AI) accelerators enables AI to run at the extreme edge, offering reduced latency, lower power cost, and improved privacy. When integrate…

cs.LG2024

DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators

Taesik Gong, Fahim Kawsar, Chulhong Min

Tiny machine learning (TinyML) aims to run ML models on small devices and is increasingly favored for its enhanced privacy, reduced latency, and low cost. Recently, the advent of t…