30 citations · 62 across the 10 of their papers we have counts for
11 papers
VLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action Models
Jaemin Kim, Jiahn Kim, Taesik Gong
Adapting vision-language-action (VLA) models to deployment-time distribution shifts is important for reliable robotic operation, but conventional first-order adaptation can exceed…
SNAP: Low-Latency Test-Time Adaptation with Sparse Updates
Hyeongheon Cha, Dong Min Kim, Hye Won Chung +2
Test-Time Adaptation (TTA) adjusts models using unlabeled test data to handle dynamic distribution shifts. However, existing methods rely on frequent adaptation and high computatio…
Test-Time Adaptation with Binary Feedback
Taeckyung Lee, Sorn Chottananurak, Junsu Kim +3
Deep learning models perform poorly when domain shifts exist between training and test data. Test-time adaptation (TTA) is a paradigm to mitigate this issue by adapting pre-trained…
By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting
Hyungjun Yoon, Biniyam Aschalew Tolera, Taesik Gong +2
Large language models (LLMs) have demonstrated exceptional abilities across various domains. However, utilizing LLMs for ubiquitous sensing applications remains challenging as exis…
SelfReplay: Adapting Self-Supervised Sensory Models via Adaptive Meta-Task Replay
Hyungjun Yoon, Jaehyun Kwak, Biniyam Aschalew Tolera +5
Self-supervised learning has emerged as a method for utilizing massive unlabeled data for pre-training models, providing an effective feature extractor for various mobile sensing a…
AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation
Taeckyung Lee, Sorn Chottananurak, Taesik Gong +1
Test-time adaptation (TTA) has emerged as a viable solution to adapt pre-trained models to domain shifts using unlabeled test data. However, TTA faces challenges of adaptation fail…
SoTTA: Robust Test-Time Adaptation on Noisy Data Streams
Taesik Gong, Yewon Kim, Taeckyung Lee +2
Test-time adaptation (TTA) aims to address distributional shifts between training and testing data using only unlabeled test data streams for continual model adaptation. However, m…
LanSER: Language-Model Supported Speech Emotion Recognition
Taesik Gong, Josh Belanich, Krishna Somandepalli +3
Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies dif…
IMG2IMU: Translating Knowledge from Large-Scale Images to IMU Sensing Applications
Hyungjun Yoon, Hyeongheon Cha, Hoang C. Nguyen +2
Pre-training representations acquired via self-supervised learning could achieve high accuracy on even tasks with small training data. Unlike in vision and natural language process…
NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation
Taesik Gong, Jongheon Jeong, Taewon Kim +3
Test-time adaptation (TTA) is an emerging paradigm that addresses distributional shifts between training and testing phases without additional data acquisition or labeling cost; on…
DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing
Taesik Gong, Yewon Kim, Adiba Orzikulova +4
Many applications utilize sensors in mobile devices and machine learning to provide novel services. However, various factors such as different users, devices, and environments impa…