T5 / BART: Unifying Every NLP Task as Text-to-Text
Categories
16 pages
LLM Architecture
GPT-3: In-Context Learning and the Few-Shot Explosion
DeepSeek-R1: Eliciting Reasoning in LLMs via Reinforcement Learning
GPT-1/2: Generative Pretraining and the Seeds of Few-Shot
BERT: What Exactly Is 'Bidirectional'?
