NLP 标签

2026

04-21

On-Policy Distillation：让学生自己犯错、自己改正

04-07

Karpathy所说的LLM Wiki

03-31

03-23

Harness Engineer

03-22

字节的M3-Agent

03-22

Attention Residuals

03-21

VeRA，LoRA-XS和TinyLoRA

03-18

腾讯的Training-Free GRPO

03-12

2025

07-19

最近阅读3-关于蒸馏，attention结构改动，和模型对齐

0%