Bo-Kyeong Kim
bokyeong1015
AI & ML interests
Network Compression, Efficient ML, Generative Models
Recent Activity
authored a paper about 19 hours ago
Quantize the Target, Quantize the Drafter: Efficient Inference with Qwen3.5-4B updated a collection 4 months ago
Efficient MoE-based LLM liked a model 4 months ago
nota-ai/Solar-Open-100B-NotaMoEQuant-NVFP4Organizations
