CosimoRulli

allRank

allRank is a framework for training learning-to-rank neural models based on PyTorch.

apb

Code for applying Automatic Prune Binarization

cosimorulli.github.io

elbm

Code for Efficient Low Bits Matrix Multiplication

ex_model_cl

Experiments on continual learning from a stream of pretrained models.

efficient_nn_for_ltr

This is the official repository of F. M. Nardini, C. Rulli, S. Trani, R. Venturini, "Distilled Neural Networks for Efficient Learning to Rank". IEEE TKDE. 2022.

JPQ

CIKM'21: JPQ substantially improves the efficiency of Dense Retrieval with 30x compression ratio, 10x CPU speedup and 2x GPU speedup.

oneDNN

oneAPI Deep Neural Network Library (oneDNN)

CosimoRulli/cosimorulli.github.io

CosimoRulli/allRank

allRank is a framework for training learning-to-rank neural models based on PyTorch.

CosimoRulli/apb

Code for applying Automatic Prune Binarization

CosimoRulli/elbm

Code for Efficient Low Bits Matrix Multiplication

CosimoRulli/ex_model_cl

Experiments on continual learning from a stream of pretrained models.