Suhyun Kim
19 papers · 2020–2025 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (49) π Academic Marathon Β· Sprint π£ Hot Topic Early Bird π Conference Polyglot Β· Silver
π
Grand Slam
π
Renaissance Researcher
(5)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(102)
Top co-authors
Research topics
Deep Learning
(15)
Machine Learning
(12)
Artificial Intelligence
(9)
Computer Vision
(8)
Application Areas
(8)
Core AI
(6)
Learning Types Β· Deep Learning
(5)
Models
(5)
Techniques
(5)
Optimization & Theory Β· Machine Learning
(4)
Learning Types Β· Machine Learning
(3)
Optimization & Theory Β· Deep Learning
(3)
Processing
(3)
Natural Language Processing
(2)
Architectures
(2)
Keywords
model compression
(4)
neural network optimization
(3)
diffusion model
(3)
knowledge distillation
(2)
federated learning
(2)
data augmentation
(2)
convolutional neural network
(2)
structured pruning
(2)
model pruning
(2)
image classification
(2)
online learning
(2)
vision transformer
(1)
image restoration
(1)
batch normalization
(1)
catastrophic forgetting
(1)
image compression
(1)
non-convex optimization
(1)
network pruning
(1)
image synthesis
(1)
image generation
(1)
Papers
Adversarial Purification via Super-Resolution and Diffusion
ICCV 2025
Convergence Analysis of Federated Learning Methods Using Backward Error Analysis
AAAI 2025
Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation
CVPR 2025
ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
ICML 2025
M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs
ACL 2025
Maximizing the Position Embedding for Vision Transformers with Global Average Pooling
AAAI 2025
Salient Frequency-aware Exemplar Compression for Resource-constrained Online Continual Learning
AAAI 2025
When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class
ICML 2025
WINS: Winograd Structured Pruning for Fast Winograd Convolution
ICCV 2025
Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN
AAAI 2024
DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism
NeurIPS 2024
REPrune: Channel Pruning via Kernel Representative Selection
AAAI 2024
Balanced Column-Wise Block Pruning for Maximizing GPU Parallelism
AAAI 2023
DepthFL : Depthwise Federated Learning for Heterogeneous Clients
ICLR 2023
GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps
AAAI 2023
Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models
ICCV 2023
Tanh Works Better with Asymmetry
NeurIPS 2023
NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency
AAAI 2022
Neuron Merging: Compensating for Pruned Neurons
NeurIPS 2020