An image enhancing pattern-based sparsity for real-time DNN execution with compiler

TBC

A Unified framework for DNN model compression using Reweighted L1 method

TBC

Automatic DNN structured pruning framework for ultra-high compression rates

TBC

Locality-aware weight pruning for fast DNN inference on GPUs

TBC

A systematic, high-efficiency ADMM-based DNN pruning framework

TBC

Compressed, quantized and optimized DNN model deployment on PIM architecture

TBC