Eunhyeok Park

papers

494

total citations

papers (14)

Fine-Grained Semantics-Aware Representation Enhancement for Self-Supervised Monocular Depth Estimation

ICCV 2021arXiv

128

citations

OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models

AAAI 2024arXiv

105

citations

FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models

ECCV 2024arXiv

citations

INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold

ICCV 2023arXiv

citations

Symmetry Regularization and Saturating Nonlinearity for Robust Quantization

ECCV 2022arXiv

citations

Grouped Speculative Decoding for Autoregressive Image Generation

ICCV 2025arXiv

citations

GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning

NEURIPS 2025arXiv

citations

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking

NEURIPS 2025arXiv

citations

PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models

CVPR 2025arXiv

citations

BASQ: Branch-Wise Activation-Clipping Search Quantization for Sub-4-Bit Neural Networks

ECCV 2022

citations

HOT: Hadamard-based Optimized Training

CVPR 2025arXiv

citations

Eunhyeok Park

papers (14)

Fine-Grained Semantics-Aware Representation Enhancement for Self-Supervised Monocular Depth Estimation

OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models

PROFIT: A Novel Training Method for sub-4-bit MobileNet Models

Temporal Dynamic Quantization for Diffusion Models

NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization

FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models

INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold

Symmetry Regularization and Saturating Nonlinearity for Robust Quantization

Grouped Speculative Decoding for Autoregressive Image Generation

GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking

PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models

BASQ: Branch-Wise Activation-Clipping Search Quantization for Sub-4-Bit Neural Networks

HOT: Hadamard-based Optimized Training

papers (14)

Fine-Grained Semantics-Aware Representation Enhancement for Self-Supervised Monocular Depth Estimation

OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models

PROFIT: A Novel Training Method for sub-4-bit MobileNet Models

Temporal Dynamic Quantization for Diffusion Models

NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization

FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models

INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold

Symmetry Regularization and Saturating Nonlinearity for Robust Quantization

Grouped Speculative Decoding for Autoregressive Image Generation

GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking

PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models

BASQ: Branch-Wise Activation-Clipping Search Quantization for Sub-4-Bit Neural Networks

HOT: Hadamard-based Optimized Training