共计 18 篇文章
2025
LANGUAGE MODEL COMPRESSION WITH WEIGHTED LOW-RANK FACTORIZATION
ASVD: ACTIVATION-AWARE SINGULAR VALUE DECOMPOSITION FOR COMPRESSING LARGE LANGUAGE MODELS
Training-Inference Mismatch In LLM KD
Dual-Space Knowledge Distillation for Large Language Models
Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation
NOT ALL LLM-GENERATED DATA ARE EQUAL: RETHINKING DATA WEIGHTING IN TEXT CLASSIFICATION
Different Designs For LLM KD Loss
从REINFORCE到PPO