token
·234 words·2 mins
LLM
test-time scaling
·4 words·1 min
RL
·108 words·1 min
reasoning
·126 words·1 min
inference-time compute scaling
·65 words·1 min
inference-compute scaling
·4 words·1 min
supervised fine-tuning
·23 words·1 min
preference tuning
·23 words·1 min
LLM training pipeline
·20 words·1 min
chain-of-thought
·136 words·1 min