GEX: A flexible method for approximating influence via Geometric Ensemble

NeurIPS 2023 GEX: A flexible method for approximating influence via Geometric Ensemble Sung-Yub Kim, Kyungsu Kim and Eunho Yang   Through a deeper understanding of predictions of neural networks, Influence Function (IF) has been applied to various tasks such as detectin...

Function Space Bayesian Pseudocoreset for Bayesian Neural Networks

NeurIPS 2023 Function Space Bayesian Pseudocoreset for Bayesian Neural Networks  Balhae Kim, Hyungi Lee, Juho Lee   A Bayesian pseudocoreset is a compact synthetic dataset summarizing essential information of a large-scale dataset and thus can be used as a proxy da...

StyleLipSync: Style-based Personalized Lip-sync Video Generation

ICCV 2023 StyleLipSync: Style-based Personalized Lip-sync Video Generation Taekyung Ki, Dongchan Min  In this paper, we present StyleLipSync, a style-based personalized lip-sync video generative model that can generate identity-agnostic lip-synchronizing video from arbitrary audi...

PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label

ICCV 2023 PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label   Joonhyung Park, Hyunjin Seo and Eunho Yang   Understanding point clouds captured from the real-world is challenging due to shifts in data d...

TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification

ICML 2022 TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification Jaeyun Song, Joonhyung Park, Eunho Yang  Learning unbiased node representations under class-imbalanced graph data is challenging due to interactions between adjacent nodes. Existing studies have in...

Skill-based Meta-Reinforcement Learning

ICLR 2022 Skill-based Meta-Reinforcement Learning Taewook Nam, Shao-Hua Sun, Karl Pertsch, Sung Ju Hwang, Joseph J Lim    While deep reinforcement learning methods have shown impressive results in robot learning, their sample inefficiency makes the learning of complex, long-...

Set-based Meta-Interpolation for Few-Task Meta-Learning

NeurIPS 2022 Set-based Meta-Interpolation for Few-Task Meta-Learning Seanie Lee, Bruno Andreis, Kenji Kawaguchi, Juho Lee, Sung Ju Hwang  Meta-learning approaches enable machine learning systems to adapt to new tasks given few examples by leveraging knowledge from related tasks. ...

Representational Continuity for Unsupervised Continual Learning

ICLR 2022 Representational Continuity for Unsupervised Continual Learning Divyam Madaan, Jaehong Yoon, Yuanchun Li, Yunxin Liu, Sung Ju Hwang  Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advanc...

Set Based Stochastic Subsampling

ICML 2022 Set Based Stochastic Subsampling Bruno Andreis, Seanie Lee, A. Tuan Nguyen, Juho Lee, Eunho Yang, Sung Ju Hwang  Deep models are designed to operate on huge volumes of high dimensional data such as images. In order to reduce the volume of data these models must process,...

Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning

ICLR 2022 Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning Seanie Lee, Hae Beom Lee, Juho Lee, Sung Ju Hwang  Multilingual models jointly pretrained on multiple languages have achieved remarkable performance on various multilingual downstream tasks. Mor...