Carlos Jimenez

data multiplexing (3) transfer learning (2) inference throughput (2) efficient computing (2) model compression (2) throughput optimization (1) inference optimization (1) pre-trained language model (1) self-attention network (1) model efficiency (1) inference speedup (1) sentence embedding (1) semantic textual similarity (1) text similarity (1) parameter efficient tuning (1) conditional similarity (1) multi-input multi-output (1) neural network (1) demultiplexing layer (1) high throughput (1)