各类基于决策单调性的dp优化
Training-Inference Mismatch In LLM KD
群作用
Burnside 引理
Different Designs For LLM KD Loss
Importance-Aware Data Selection for Efficient LLM Instruction Tuning
Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory
Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
Training-Inference Mismatch In LLM KD(II)
FROM CORRECTION TO MASTERY: REINFORCED DISTILLATION OF LARGE LANGUAGE MODEL AGENTS