James Seale Smith

multi-head attention (2) mixture of expert (2) large language model (2) vision-language model (2) state-space model (2) language model (2) continual learning (2) attention mechanism (1) language modeling (1) model architecture (1) data-free learning (1) prompt learning (1) neural network optimization (1) efficient computing (1) model pruning (1) weight sharing (1) fine-grained recognition (1) synthetic datum (1) vision language model (1) parameter-efficient fine-tuning (1)