5 citations · 10 across the 6 of their papers we have counts for
6 papers
Not All Task Vectors Need Equal Rank: Energy-Proportional Allocation for Model Merging
Hyunjoong Cho, Jinhyeok Jang
Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional joint training. Recent spectral me…
A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM
ByungOk Han, Jaehong Kim, Jinhyeok Jang
Vision-Language-Action (VLA) models are receiving increasing attention for their ability to enable robots to perform complex tasks by integrating visual context with linguistic com…
ETRI-Activity3D: A Large-Scale RGB-D Dataset for Robots to Recognize Daily Activities of the Elderly
Jinhyeok Jang, Dohyung Kim, Cheonshu Park +3
Deep learning, based on which many modern algorithms operate, is well known to be data-hungry. In particular, the datasets appropriate for the intended application are difficult to…
Neural Networks with Activation Networks
Jinhyeok Jang, Jaehong Kim, Jaeyeon Lee +1
This work presents an adaptive activation method for neural networks that exploits the interdependency of features. Each pixel, node, and layer is assigned with a polynomial activa…
Efficient architecture for deep neural networks with heterogeneous sensitivity
Hyunjoong Cho, Jinhyeok Jang, Chanhyeok Lee +1
This work presents a neural network that consists of nodes with heterogeneous sensitivity. Each node in a network is assigned a variable that determines the sensitivity with which…
Deep Asymmetric Networks with a Set of Node-wise Variant Activation Functions
Jinhyeok Jang, Hyunjoong Cho, Jaehong Kim +2
This work presents deep asymmetric networks with a set of node-wise variant activation functions. The nodes' sensitivities are affected by activation function selections such that…