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
SVD Decompositon in LLM Compression
DipSVD: Dual-importance Protected SVD for Efficient LLM Compression
SVD-LLM: TRUNCATION-AWARE SINGULAR VALUE DECOMPOSITION FOR LARGE LANGUAGE MODEL COMPRESSION
LANGUAGE MODEL COMPRESSION WITH WEIGHTED LOW-RANK FACTORIZATION
ASVD: ACTIVATION-AWARE SINGULAR VALUE DECOMPOSITION FOR COMPRESSING LARGE LANGUAGE MODELS
Dual-Space Knowledge Distillation for Large Language Models