Probabilistic feature matching for fast scalable visual promptingThomas FrickCezary Skuraet al.2024IJCAI 2024
QAttn: Efficient GPU Kernels for mixed-precision vision transformersPiotr Sebastian KluskaAdrián Castellóet al.2024CVPR 2024
Challenges in post-training quantization of Vision TransformersPiotr Sebastian KluskaFlorian Scheideggeret al.2023KDD 2023