Zhikai Li

I-ViT. [ICCV 2023] I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference

RepQ-ViT. [ICCV 2023] RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers

PSAQ-ViT. [ECCV 2022] Patch Similarity Aware Data-Free Quantization for Vision Transformers

HTQ. [PR 2024] HTQ: Exploring the High-Dimensional Trade-Off of Mixed-Precision Quantization

K-Sort-Eval. [ICLR 2026] K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge

DFQ-SAM. Python