Hyunwoo Kim

13

Papers

195

Total Citations

1

Affiliations

Affiliations

NVIDIA

Papers (13)

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

Learning Equi-angular Representations for Online Continual Learning

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

Geometry in Style: 3D Stylization via Surface Normal Deformation

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

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

Perception Prioritized Training of Diffusion Models

Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis

Representation Shift: Unifying Token Compression with FlashAttention

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

Learning Not to Learn: Training Deep Neural Networks With Biased Data

Manifold-valued Dirichlet Processes

Curiosity-Bottleneck: Exploration By Distilling Task-Specific Novelty