王云鹤 ,  盘古大模型 ,  模型压缩

xi-yin ,  string-theory ,  higher-spin-theory ,  theoretical ,  physicist

researcher ,  quanquan-gu ,  llm-pretraining

scholar ,  ai-safety ,  zico-kolter ,  adversarial-robustness ,  differentiable-optimization

scholar ,  thomas-g.-dietterich ,  ensemble-methods

researcher ,  neural-architecture-search ,  post-training ,  switch-transformer ,  barret-zoph

researcher ,  rlhf ,  nathan-lambert ,  open-language-models ,  interconnects

founder ,  william-fedus ,  switch-transformer ,  mixture-of-experts ,  post-training

researcher ,  reinforcement-learning ,  tim-rocktäschel ,  open-endedness ,  neural-symbolic-reasoning

research-engineer ,  james-bradbury ,  jax ,  qrnn ,  ml-systems

researcher ,  jascha-sohl-dickstein ,  diffusion-models ,  nonequilibrium-thermodynamics ,  neural-network-theory

research-engineer ,  susan-zhang ,  opt-175b ,  lima

aran-komatsuzaki ,  gpt-j ,  sparse-upcycling ,  scaling-laws ,  laion

daniel-roy ,  probabilistic-programming ,  mondrian-process ,  pac-bayes ,  learning-theory

researcher ,  lucas-beyer ,  vision-transformer ,  siglip ,  multimodal-ai

research-engineer ,  tim-dettmers ,  qlora ,  bitsandbytes ,  quantization

scholar ,  david-duvenaud ,  neural-odes ,  autograd ,  agi-safety

scholar ,  yejin-choi ,  commonsense-ai ,  atomic ,  moral-reasoning

researcher ,  sébastien-bubeck ,  multi-armed-bandits ,  law-of-robustness ,  phi-slm

scholar ,  nlp ,  jacob-andreas ,  neural-module-networks ,  compositionality

adversarial-examples ,  researcher ,  openai ,  wojciech-zaremba ,  codex

researcher ,  durk-kingma ,  variational-autoencoder ,  adam-optimizer ,  generative-modeling

researcher ,  gumbel-softmax ,  deep-reinforcement-learning ,  shixiang-shane-gu ,  zero-shot-chain-of-thought

alec-radford ,  generative-ai ,  gpt ,  clip ,  whisper

glove ,  founder ,  richard-socher ,  prompt-engineering ,  recursive-neural-networks

chatgpt ,  mira-murati ,  x ,  thinking-machines-lab ,  human-ai-collaboration

adversarial-examples ,  christian-szegedy ,  inception-architecture ,  batch-normalization ,  autoformalization

researcher ,  seq2seq ,  quoc-v.-le ,  neural-architecture-search ,  automl

researcher ,  jason-wei ,  chain-of-thought-prompting ,  instruction-tuning ,  llm-reasoning