Tang
Zhichen
home
archives
categories
about
LLM · Agent · Post-training
Building LLMs & Agents
Home
index.html
Scroll down
唐芷晨(Zhichen Tang)
Focus:
LLM · Agent · 后训练
Interests:
RLHF · DPO · PEFT
Address:
Shanghai, China
联系我
Technique
7
查看分类
最近发布
Technique
多轮 Agent 强化学习中的信用分配:从 Session Reward 到 Turn Advantage
26/09/11
10:30
Technique
大模型应用岗位问答手册
25/08/25
11:28
Technique
LangChain
25/08/22
11:56
Technique
LangGraph
25/08/21
11:11
Technique
LoRA (Low-Rank Adaptation)
25/08/16
11:11
Technique
C++ 面试速成代码合集
25/06/26
11:11
Technique
Paper Outline
25/05/30
17:18
1