Eunhyeok Park

15

Papers

119

Total Citations

Papers (15)

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

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

Grouped Speculative Decoding for Autoregressive Image Generation

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

Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss

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

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

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

Symmetry Regularization and Saturating Nonlinearity for Robust Quantization

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

HOT: Hadamard-based Optimized Training

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

Weighted-Entropy-Based Quantization for Deep Neural Networks

NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization

Temporal Dynamic Quantization for Diffusion Models