U Kang

Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression

STABLE: Shift-Tolerant Allocation via Black-Litterman Using Conditional Diffusion Estimates

DiaQ: Direction-aware Activation Quantization for Fast and Accurate Model Inference

SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning

FlexBCQ: Flexible Binary-coding Quantization for Large Language Models