9 citations · 11 across the 10 of their papers we have counts for
10 papers
Personalized Object Identification and Localization via In-Context Inference with Vision-Language Models
Kensuke Nakamura, Byung-Woo Hong
Personalized object localization (POL) localizes an object instance in a query image based on a few reference images with bounding-box annotations and a target object label. The pi…
Emergent Coordination through Game-Induced Nonlinear Opinion Dynamics
Haimin Hu, Kensuke Nakamura, Kai-Chieh Hsu +2
We present a multi-agent decision-making framework for the emergent coordination of autonomous agents whose intents are initially undecided. Dynamic non-cooperative games have been…
Online Update of Safety Assurances Using Confidence-Based Predictions
Kensuke Nakamura, Somil Bansal
Robots such as autonomous vehicles and assistive manipulators are increasingly operating in dynamic environments and close physical proximity to people. In such scenarios, the robo…
Parameter-Conditioned Reachable Sets for Updating Safety Assurances Online
Javier Borquez, Kensuke Nakamura, Somil Bansal
Hamilton-Jacobi (HJ) reachability analysis is a powerful tool for analyzing the safety of autonomous systems. However, the provided safety assurances are often predicated on the as…
Decentralized Learning With Limited Communications for Multi-robot Coverage of Unknown Spatial Fields
Kensuke Nakamura, María Santos, Naomi Ehrich Leonard
This paper presents an algorithm for a team of mobile robots to simultaneously learn a spatial field over a domain and spatially distribute themselves to optimally cover it. Drawin…
Generative Adversarial Networks via a Composite Annealing of Noise and Diffusion
Kensuke Nakamura, Simon Korman, Byung-Woo Hong
Generative adversarial network (GAN) is a framework for generating fake data using a set of real examples. However, GAN is unstable in the training stage. In order to stabilize GAN…
Regularization in network optimization via trimmed stochastic gradient descent with noisy label
Kensuke Nakamura, Bong-Soo Sohn, Kyoung-Jae Won +1
Regularization is essential for avoiding over-fitting to training data in network optimization, leading to better generalization of the trained networks. The label noise provides a…
Stochastic batch size for adaptive regularization in deep network optimization
Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong
We propose a first-order stochastic optimization algorithm incorporating adaptive regularization applicable to machine learning problems in deep learning framework. The adaptive re…
Adaptive Weight Decay for Deep Neural Networks
Kensuke Nakamura, Byung-Woo Hong
Regularization in the optimization of deep neural networks is often critical to avoid undesirable over-fitting leading to better generalization of model. One of the most popular re…
Block-Cyclic Stochastic Coordinate Descent for Deep Neural Networks
Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong
We present a stochastic first-order optimization algorithm, named BCSC, that adds a cyclic constraint to stochastic block-coordinate descent. It uses different subsets of the data…