8 citations · 11 across the 10 of their papers we have counts for
15 papers
Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration
Hyeongheon Cha, Young D. Kwon, Sung-Ju Lee
Post-training quantization is a standard route to fitting vision transformers (ViTs) into edge compute and memory budgets, yet quantized models become especially brittle under dist…
Monte Carlo Estimation for KV Cache Eviction
Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer +5
Most KV-cache eviction methods ask, in effect, which memory appeared important while reading the prompt? We instead ask which memory will matter while answering? Since decoding que…
On the Interaction Between Model Compression and Test-Time Adaptation
Francesco Corti, Dong Wang, Young D. Kwon +2
Deep neural networks deployed in the wild must be both efficient and adaptable, requiring model compression and test-time adaptation (TTA). While both are well studied in isolation…
Speculative Decoding with a Speculative Vocabulary
Miles Williams, Young D. Kwon, Rui Li +2
Speculative decoding has rapidly emerged as a leading approach for accelerating language model (LM) inference, as it offers substantial speedups while yielding identical outputs. T…
Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation
Sudarshan Sreeram, Young D. Kwon, Cecilia Mascolo
Test-time adaptation (TTA) offers a compelling remedy for machine learning (ML) models that degrade under domain shifts, improving generalisation on-the-fly with only unlabelled sa…
Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive Tiling
Young D. Kwon, Abhinav Mehrotra, Malcolm Chadwick +2
High-resolution (4K) image-to-image synthesis has become increasingly important for mobile applications. Existing diffusion models for image editing face significant challenges, in…
EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems
Xiao Ma, Young D. Kwon, Dong Ma
Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poo…
LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices
Cynthia Dong, Hong Jia, Young D. Kwon +2
While there are many advantages to deploying machine learning models on edge devices, the resource constraints of mobile platforms, the dynamic nature of the environment, and diffe…
UR2M: Uncertainty and Resource-Aware Event Detection on Microcontrollers
Hong Jia, Young D. Kwon, Dong Ma +4
Traditional machine learning techniques are prone to generating inaccurate predictions when confronted with shifts in the distribution of data between the training and testing phas…
LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms
Young D. Kwon, Jagmohan Chauhan, Hong Jia +2
Continual Learning (CL) allows applications such as user personalization and household robots to learn on the fly and adapt to context. This is an important feature when context, a…
TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
Young D. Kwon, Rui Li, Stylianos I. Venieris +3
On-device training is essential for user personalisation and privacy. With the pervasiveness of IoT devices and microcontroller units (MCUs), this task becomes more challenging due…
YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers
Young D. Kwon, Jagmohan Chauhan, Cecilia Mascolo
With the advancement of Deep Neural Networks (DNN) and large amounts of sensor data from Internet of Things (IoT) systems, the research community has worked to reduce the computati…
Enabling On-Device Smartphone GPU based Training: Lessons Learned
Anish Das, Young D. Kwon, Jagmohan Chauhan +1
Deep Learning (DL) has shown impressive performance in many mobile applications. Most existing works have focused on reducing the computational and resource overheads of running De…
FastICARL: Fast Incremental Classifier and Representation Learning with Efficient Budget Allocation in Audio Sensing Applications
Young D. Kwon, Jagmohan Chauhan, Cecilia Mascolo
Various incremental learning (IL) approaches have been proposed to help deep learning models learn new tasks/classes continuously without forgetting what was learned previously (i.…
Knowing when we do not know: Bayesian continual learning for sensing-based analysis tasks
Sandra Servia-Rodriguez, Cecilia Mascolo, Young D. Kwon
Despite much research targeted at enabling conventional machine learning models to continually learn tasks and data distributions sequentially without forgetting the knowledge acqu…