docs: add English README + emphasize HTML cross-device readability

- README.md: new 📱 section highlighting MathJax / highlight.js / responsive
  layout / sticky TOC / single-file offline-ready HTML; bilingual link to EN
- README_EN.md (new): full English translation, mirror structure
- repo description: bilingual one-liner + HTML readability point

Author: wanshuiyin

README.md

@@ -5,10 +5,22 @@
 # ARIS in 秋招
 
 > 希望大家秋招的时候轻松一点 🌱
+>
+> 📖 **English version**: [README_EN.md](README_EN.md)
 
 中文 ML / LLM / 多模态 / 生成式面试 cheat sheet 合集，由 **[ARIS — Auto Research in Sleep](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)** 的 `/render-html` workflow 自动生成。
 
-每篇都是一份长文 + 公式 + 从零开始的 PyTorch 代码 + 25 高频面试题（L1 必会 · L2 进阶 · L3 顶级 lab）；HTML 渲染为 academic-newspaper 排版，sticky TOC + MathJax + 代码高亮，**手机和 iPad 上读都不糊**。
+每篇都是一份长文 + 公式 + 从零开始的 PyTorch 代码 + 25 高频面试题（L1 必会 · L2 进阶 · L3 顶级 lab）。
+
+### 📱 HTML 格式哪里都能读，清清楚楚
+
+地铁上掏手机、咖啡馆开 iPad、图书馆开笔记本——同一个 HTML 链接打开都能读：
+
+- 🧮 **MathJax** 渲染所有 LaTeX 公式（**不是截图**，可缩放、可复制、可选中）
+- 💻 **highlight.js** 给 PyTorch 代码高亮上色
+- 📐 **响应式排版** 自动适配窗口宽度，不糊不溢出
+- 📑 **Sticky TOC** 长文里随时跳转章节
+- 💾 **单文件 HTML**，下载就能离线读，不依赖任何后端
 
 ---
 

README_EN.md

@@ -0,0 +1,117 @@
+<p align="center">
+  <img src="assets/aris_logo.svg" alt="ARIS — Auto Research in Sleep" width="640">
+</p>
+
+# ARIS in 秋招 (AI Offer Tutorials)
+
+> Hoping to make your **秋招 (qiūzhāo, Chinese AI campus recruiting season)** a little easier 🌱
+>
+> 📖 **中文版**: [README.md](README.md)
+
+A curated collection of Chinese ML / LLM / Multimodal / Generative-Model interview cheat sheets, auto-generated by the **[ARIS — Auto Research in Sleep](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)** `/render-html` workflow.
+
+Each cheat sheet is a long-form Chinese tutorial with: formula derivations · from-scratch PyTorch code · 25 high-frequency interview questions (L1 essentials · L2 advanced · L3 top-tier lab).
+
+### 📱 HTML reads cleanly everywhere
+
+Phone on the subway, iPad at a café, laptop in the library — same HTML link opens equally well:
+
+- 🧮 **MathJax** renders all LaTeX formulas (**not screenshots** — scalable, copyable, selectable)
+- 💻 **highlight.js** colors all PyTorch code blocks
+- 📐 **Responsive layout** adapts to any window width — no overflow, no blur
+- 📑 **Sticky TOC** for jumping around long documents
+- 💾 **Single-file HTML** — download once, read offline, no backend required
+
+---
+
+## 🌟 What is ARIS — A Quick Pitch
+
+[**ARIS — Auto Research in Sleep**](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep) is one of the most-watched AI research agent skill platforms of 2025-2026. The `/interview-cheatsheet` + `/render-html` skills that produced this repo are 2 out of ARIS's 74+ skills.
+
+[![Stars](https://img.shields.io/github/stars/wanshuiyin/Auto-claude-code-research-in-sleep?style=flat&logo=github&logoColor=white&color=gold&label=Stars)](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/stargazers) · [![arXiv](https://img.shields.io/badge/arXiv-2605.03042-b31b1b?style=flat&logo=arxiv)](https://huggingface.co/papers/2605.03042) · [![HF Daily #1](https://img.shields.io/badge/HF%20Daily%20Papers-%231-yellow?style=flat)](https://huggingface.co/papers/2605.03042) · [![PaperWeekly](https://img.shields.io/badge/Featured%20on-PaperWeekly-red?style=flat)](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep) · [![awesome-agent-skills](https://img.shields.io/badge/Featured%20in-awesome--agent--skills-blue?style=flat&logo=github)](https://github.com/VoltAgent/awesome-agent-skills) · [![Project of the Day](https://img.shields.io/badge/AI%20Digital%20Crew-Project%20of%20the%20Day-orange?style=flat)](https://aidigitalcrew.com)
+
+- ⭐ **~10k GitHub stars** — top-trending AI agent repo
+- 🥇 **HuggingFace Daily Papers #1** — top of the day, paper [arXiv:2605.03042](https://huggingface.co/papers/2605.03042)
+- 🏆 **AI Digital Crew · Project of the Day** (2026.03.14)
+- 📰 **Featured on PaperWeekly** + **VoltAgent/awesome-agent-skills**
+- 🛠️ **74+ research skills** — full lifecycle from idea exploration → experiments → papers → rebuttals → talk slides
+- 🌐 **7+ platforms supported** — Claude Code · Codex CLI · Cursor · Trae · Antigravity · GitHub Copilot CLI · OpenClaw
+- 🔧 **ARIS-Code standalone CLI** — multi-provider runtime, no Claude Code dependency required
+
+Core methodology: **cross-model adversarial review** — executor and reviewer must come from different model families (Claude × GPT-5.5 xhigh × Gemini), so no LLM ever judges its own output. This protocol carries directly into interview cheat sheet generation: every formula, code block, and citation in every tutorial passes an independent audit (see each `.review.json` audit trail).
+
+👉 **ARIS main repo**: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
+
+---
+
+## 📚 Tutorial Index
+
+### 🧠 General / Foundations
+
+| Topic | HTML (recommended) | Source MD |
+|---|---|---|
+| **Attention Interview Cheat Sheet** | [📄 HTML](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/attention_tutorial.html) | [MD](docs/tutorials/attention_tutorial.md) |
+
+### 🎯 Post-Training & Reasoning
+
+| Topic | HTML | MD |
+|---|---|---|
+| RLHF / DPO / GRPO / PPO | 🚧 | — |
+| Reasoning Models (o1 / R1 / Test-Time Compute / PRM) | 🚧 | — |
+
+### 🏛️ LLM Architecture & Systems
+
+| Topic | HTML | MD |
+|---|---|---|
+| MoE (DeepSeek-V3 / Mixtral / Llama 4) | 🚧 | — |
+| Long Context (RoPE / YaRN / NTK / MLA / StreamingLLM) | 🚧 | — |
+| KV Cache + Speculative Decoding (Medusa / EAGLE / MLA) | 🚧 | — |
+| Quantization (GPTQ / AWQ / FP8 / NVFP4 / SmoothQuant) | 🚧 | — |
+| Distributed Training (DDP / FSDP2 / ZeRO / TP / PP / EP / SP) | 🚧 | — |
+
+### 🌊 Generative Models — Theory & Tokenizers
+
+| Topic | HTML | MD |
+|---|---|---|
+| **Flow Matching Quick Reference** | [📄 HTML](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/flow_matching_tutorial.html) | [MD](docs/tutorials/flow_matching_tutorial.md) |
+| Diffusion Foundations (DDPM / Score / DDIM / EDM / CFG) | 🚧 | — |
+| VAE / VQ-VAE / VQ-GAN / FSQ | 🚧 | — |
+
+### 🎨 Generation Systems — Image / Video / 3D
+
+| Topic | HTML | MD |
+|---|---|---|
+| Image Gen Systems (LDM / SD / SDXL / SD3 / FLUX / ControlNet) | 🚧 | — |
+| Video Gen (Sora / Hunyuan-Video / Kling / Wan / Movie Gen) | 🚧 | — |
+| 3D Gen (NeRF / Instant-NGP / 3DGS / SDS / Trellis) | 🚧 | — |
+
+### 👁️ Multimodal
+
+| Topic | HTML | MD |
+|---|---|---|
+| VLM (CLIP / LLaVA / Qwen-VL / DeepSeek-VL) | 🚧 | — |
+
+> 🚧 = in flight. Several background agents are writing these now; rows fill in as they finish.
+
+---
+
+## 🤖 How These Are Generated
+
+Every tutorial uses ARIS's `/interview-cheatsheet` skill:
+
+1. **Plan** — 12-14 sections (TL;DR · Intuition · Formulas · Code · Variants · Complexity · 25 Q&A)
+2. **Draft** — 600-1000 lines of Chinese tutorial + runnable from-scratch PyTorch
+3. **Cross-model review** — fresh-thread codex GPT-5.5 xhigh audit on 10 properties (formula correctness · code runnability · citation accuracy · table-pipe escapes · callout style · personal-info leak · ...)
+4. **Fix loop ≤ 3 rounds**
+5. **`/render-html`** — single-file HTML render + 13-property render audit (information fidelity · TOC · math · code highlight · safety · privacy · ...)
+6. **`.review.json`** — full audit trail saved next to each tutorial
+
+Cross-model adversarial review (executor ≠ reviewer family) is ARIS's core invariant: an LLM auditing its own output is no audit.
+
+---
+
+## License
+
+[MIT](LICENSE) — use, modify, share, fork freely. Hope this helps your job search. 💪
+
+PRs welcome if you write new cheat sheets and want to contribute them.