Jinwoo Kim

Affiliations

KAIST

papers

498

total citations

papers (15)

Pure Transformers are Powerful Graph Learners

NEURIPS 2022arXiv

258

citations

SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data

CVPR 2021arXiv

104

citations

UBoCo: Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection

CVPR 2022arXiv

citations

Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models

CVPR 2025arXiv

citations

Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing

CVPR 2024arXiv

citations

Revisiting Random Walks for Learning on Graphs

ICLR 2025arXiv

citations

Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost

NEURIPS 2022arXiv

citations

ORIDa: Object-centric Real-world Image Composition Dataset

CVPR 2025arXiv

citations

3D Denoisers Are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation

AAAI 2025arXiv

citations

Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm Under Mixed Illumination

ICCV 2021

citations

Transformers Generalize DeepSets and Can be Extended to Graphs & Hypergraphs

NEURIPS 2021

citations

A Brand New Dance Partner: Music-Conditioned Pluralistic Dancing Controlled by Multiple Dance Genres

CVPR 2022

citations

Jinwoo Kim

Affiliations

papers (15)

Pure Transformers are Powerful Graph Learners

SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data

UBoCo: Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection

Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning

Equivariant Hypergraph Neural Networks

Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models

Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing

Revisiting Random Walks for Learning on Graphs

Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost

ORIDa: Object-centric Real-world Image Composition Dataset

3D Denoisers Are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation

Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm Under Mixed Illumination

Transformers Generalize DeepSets and Can be Extended to Graphs & Hypergraphs

A Brand New Dance Partner: Music-Conditioned Pluralistic Dancing Controlled by Multiple Dance Genres

papers (15)

Pure Transformers are Powerful Graph Learners

SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data

UBoCo: Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection

Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning

Equivariant Hypergraph Neural Networks

Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models

Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing

Revisiting Random Walks for Learning on Graphs

Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost

ORIDa: Object-centric Real-world Image Composition Dataset

3D Denoisers Are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation

Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm Under Mixed Illumination

Transformers Generalize DeepSets and Can be Extended to Graphs & Hypergraphs

A Brand New Dance Partner: Music-Conditioned Pluralistic Dancing Controlled by Multiple Dance Genres