Strategically Diverse Sampling for Self-Training
Strategically diverse sampling for LLM self-training beats IID data, and Qwen3-4B incorrect traces beat a 235B teacher.
2 stories, newest first · one card per story
Strategically diverse sampling for LLM self-training beats IID data, and Qwen3-4B incorrect traces beat a 235B teacher.
Separating design-direction exploration from code generation via structured specifications broadens UI alternatives without destabilizing output.
Today 1.6K readers · 2.5K views · 785 reads · all time 189K views