Skip to content
View ManagerZhang10's full-sized avatar
  • ByteDance
  • Haidian,Beijing

Block or report ManagerZhang10

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ManagerZhang10/README.md

张指导 · 大模型笔记

用动效把多模态和生成模型讲明白。

🎬 全部动效 → managerzhang10.github.io 30 集,178 个知识点,每一集都能在网页里播放、按知识点跳转。


从噪声画出图

Flow-GRPO:把强化学习用到生图上

生图模型如何实现连续强度控制

AI 怎么看懂图片和视频

VAR:把 GPT 生图改成由粗到细

SRPO:一张图、两句话训 FLUX
系列 讲什么
多模态原理 · 理解篇 看图的大模型怎么把图读进去、怎么训出来(Qwen3-VL-8B,4 集)
生成原理 生图模型怎么从噪声画出图、怎么训、怎么编辑、怎么评测(Qwen-Image,13 集)
论文解读 一期讲透一篇论文
VividPaper 把一篇论文做成 3 分钟动效解读的 Agent skill

小红书 张指导 大模型笔记 · 抖音 张指导 大模型笔记

Pinned Loading

  1. agentic-rl-from-scratch agentic-rl-from-scratch Public

    No GPU, no LLM — agentic RL from scratch in pure Python. 不用 GPU、不用 LLM,纯 Python 手搓明白 Agentic RL 训练闭环(trajectory / reward / loss mask / GRPO)

    Python 6