Hyunwoo J. Kim

10

Papers

81

Total Citations

Papers (10)

Prompt Learning via Meta-Regularization

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality

VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning

Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems

Super-Class Guided Transformer for Zero-Shot Attribute Classification

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation

vid-TLDR: Training Free Token Merging for Light-weight Video Transformer

Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection

Retrieval-Augmented Open-Vocabulary Object Detection

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers