Jin-Hwa Kim

Affiliations

NAVER AI Lab

papers

509

total citations

papers (12)

Dense Text-to-Image Generation with Attention Modulation

ICCV 2023arXiv

187

citations

Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation

ICLR 2024arXiv

155

citations

Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty

NEURIPS 2022arXiv

citations

Mutual Information Divergence: A Unified Metric for Multimodal Generative Models

NEURIPS 2022arXiv

citations

Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models

ICCV 2023arXiv

citations

PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency

ICML 2024arXiv

citations

Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs

ICML 2024arXiv

citations

Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models

NEURIPS 2025arXiv

citations

OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematics

ICCV 2025arXiv

citations

Jin-Hwa Kim

Affiliations

papers (12)

Dense Text-to-Image Generation with Attention Modulation

Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation

Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty

Mutual Information Divergence: A Unified Metric for Multimodal Generative Models

SelecMix: Debiased Learning by Contradicting-pair Sampling

The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training

3D-aware Blending with Generative NeRFs

Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models

PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency

Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs

Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models

OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematics

papers (12)

Dense Text-to-Image Generation with Attention Modulation

Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation

Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty

Mutual Information Divergence: A Unified Metric for Multimodal Generative Models

SelecMix: Debiased Learning by Contradicting-pair Sampling

The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training

3D-aware Blending with Generative NeRFs

Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models

PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency

Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs

Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models

OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematics