Hyunwoo Kim

Affiliations

NVIDIA

papers

652

total citations

papers (11)

Perception Prioritized Training of Diffusion Models

CVPR 2022arXiv

336

citations

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

ICLR 2024arXiv

166

citations

Bridging the Gap Between Classification and Localization for Weakly Supervised Object Localization

CVPR 2022arXiv

citations

VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation

CVPR 2022arXiv

citations

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

ICCV 2025arXiv

citations

Representation Shift: Unifying Token Compression with FlashAttention

ICCV 2025arXiv

citations

Hyunwoo Kim

Affiliations

papers (11)

Perception Prioritized Training of Diffusion Models

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

Bridging the Gap Between Classification and Localization for Weakly Supervised Object Localization

VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation

Learning Equi-angular Representations for Online Continual Learning

Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models

Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis

VVS: Video-to-Video Retrieval with Irrelevant Frame Suppression

Geometry in Style: 3D Stylization via Surface Normal Deformation

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

Representation Shift: Unifying Token Compression with FlashAttention

papers (11)

Perception Prioritized Training of Diffusion Models

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

Bridging the Gap Between Classification and Localization for Weakly Supervised Object Localization

VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation

Learning Equi-angular Representations for Online Continual Learning

Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models

Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis

VVS: Video-to-Video Retrieval with Irrelevant Frame Suppression

Geometry in Style: 3D Stylization via Surface Normal Deformation

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

Representation Shift: Unifying Token Compression with FlashAttention