Suhyun Kim

papers

total citations

papers (12)

Neuron Merging: Compensating for Pruned Neurons

NEURIPS 2020arXiv

citations

Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models

ICCV 2023arXiv

citations

Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN

AAAI 2024arXiv

citations

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety

ICML 2025arXiv

citations

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling

AAAI 2025arXiv

citations

REPrune: Channel Pruning via Kernel Representative Selection

AAAI 2024arXiv

citations

Salient Frequency-aware Exemplar Compression for Resource-constrained Online Continual Learning

AAAI 2025

citations

Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation

CVPR 2025arXiv

citations

Convergence Analysis of Federated Learning Methods Using Backward Error Analysis

AAAI 2025arXiv

citations

Suhyun Kim

papers (12)

Neuron Merging: Compensating for Pruned Neurons

Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models

Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling

REPrune: Channel Pruning via Kernel Representative Selection

Salient Frequency-aware Exemplar Compression for Resource-constrained Online Continual Learning

Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation

Tanh Works Better with Asymmetry

WINS: Winograd Structured Pruning for Fast Winograd Convolution

Adversarial Purification via Super-Resolution and Diffusion

Convergence Analysis of Federated Learning Methods Using Backward Error Analysis

papers (12)

Neuron Merging: Compensating for Pruned Neurons

Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models

Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling

REPrune: Channel Pruning via Kernel Representative Selection

Salient Frequency-aware Exemplar Compression for Resource-constrained Online Continual Learning

Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation

Tanh Works Better with Asymmetry

WINS: Winograd Structured Pruning for Fast Winograd Convolution

Adversarial Purification via Super-Resolution and Diffusion

Convergence Analysis of Federated Learning Methods Using Backward Error Analysis