Bumsub Ham

8

Papers

27

Total Citations

Papers (8)

Instance-Aware Group Quantization for Vision Transformers

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety

Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions

Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients

Scheduling Weight Transitions for Quantization-Aware Training

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling

Subnet-Aware Dynamic Supernet Training for Neural Architecture Search

AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search