Pages 26–30 of NTU’s second lecture compare resetting a model for each input with carrying its updates forward. Rotation prediction, noisy speech recognition, and experience replay show how to measure both adaptation and forgetting.
Topic: #fine-tuning
A collection of 4 posts about fine-tuning.
19 min read
• #self-improvement#test-time-training#test-time-adaptation
Pages 21–25 connect ExpRAG, BetterTogether and E-SPL. Papers and Omar Khattab’s lecture explain experience retrieval, alternating optimization and reevaluation when goals change.
20 min read
• #self-improvement#ai-agents#prompt-optimization
PostTrainBench and FT-Dojo distinguish the training agent from the target model and examine time budgets, weighted scores and data contamination.
18 min read
• #self-improvement#post-training#llm-agents
Worked examples contrast revising an answer with updating parameters through supervised learning on corrections or reinforcement learning on revision actions.
22 min read
• #self-improvement#self-correction#reinforcement-learning