2026  9

八月  2

Backend Basic

Created: 2026-08-12 · Updated: 2026-08-12 · 9 分钟 · 4259 字 · dengkoicat

Harness Engineering for Self-Improvement

Created: 2026-08-04 · Updated: 2026-08-04 · 29 分钟 · 14117 字 · Lilian Weng

七月  5

Agentic RAG

Created: 2026-07-28 · Updated: 2026-07-28 · 7 分钟 · 3036 字 · DengKoicat

Agent Harness

Created: 2026-07-24 · Updated: 2026-07-24 · 41 分钟 · 20275 字 · DengKoicat

Reinforcement Learning for LLMs

Created: 2026-07-06 · Updated: 2026-07-06 · 31 分钟 · 15340 字 · dengkoicat

Policy Gradient with Baseline

Created: 2026-07-05 · Updated: 2026-07-05 · 5 分钟 · 2405 字 · dengkoicat

Reinforement Learning

Created: 2026-07-02 · Updated: 2026-07-02 · 11 分钟 · 5117 字 · dengkoicat

六月  2

PEFT: Parameter-Efficient Fine-Tuning

Created: 2026-06-14 · Updated: 2026-06-14 · 12 分钟 · 5883 字 · dengkoicat

Transformer

Created: 2026-06-09 · Updated: 2026-06-09 · 8 分钟 · 3612 字 · DengKoicat