Tags
deep-learning 49 nlp 15 computer-vision 10 attention 10 optimization 8 architecture 8 generative 7 reinforcement-learning 7 training 6 rnn 6 cnn 5 transformer 5 foundation-models 5 theory 5 language-models 3 reasoning 3 complexity 3 regularization 3 transformers 3 seq2seq 3 fundamentals 2 pre-training 2 multimodal 2 entropy 2 diffusion 2 trees 2 information-theory 2 policy-gradient 2 mdl 2 compression 2 memory 2 agents 2 residual 2 lstm 2 imagenet 1 paper 1 neural-networks 1 translation 1 prompting 1 automata 1 physics 1 course 1 speech 1 ctc 1 segmentation 1 games 1 classic 1 machine-learning 1 ensemble 1 boosting 1 distributed 1 parallelism 1 emergent-abilities 1 computation 1 agi 1 intelligence 1 aixi 1 sequence-modeling 1 efficiency 1 model-selection 1 gnn 1 chemistry 1 graphs 1 tabular-data 1 differentiable 1 sets 1 combinatorial 1 inference 1 long-context 1 decision-making 1 visual-qa 1 alignment 1 encoder-decoder 1 scaling 1 algorithm 1 matching 1 game-theory 1 autoencoder 1 latent-space 1 vae 1 embeddings 1 representation-learning 1 web-agents 1 benchmark 1