ARIS-in-AI-Offer (ARIS in 秋招)
Hoping to make your 秋招 (qiūzhāo, Chinese AI campus recruiting season) a little easier 🌱
📖 中文版 (Chinese version): README_CN.md
📚 Jump to a topic — 33 first-party cheat sheets across 7 categories + 1 community-contributed category:
🧠 General / Foundations · 🎯 Post-Training & Reasoning · 🏛️ LLM Architecture & Systems · 🌊 Generative Models — Theory & Tokenizers · 🎨 Generation Systems (Image / Video / 3D / Diffusion Post-Training) · 👁️ Multimodal · 🤖 Agents · 🦾 Embodied AI / 具身智能
Or browse the full 📚 Tutorial Index ↓ · jump to 🌐 ARIS-Homepage ↓.
🏆 Built on a battle-tested foundation — the ARIS main repo has ~10k GitHub stars, was HuggingFace Daily Papers #1, won AI Digital Crew Project of the Day, and ships 74+ research skills across 7+ platforms. This isn't a vaporware preview — every cheat sheet here is the production output of the same
/interview-cheatsheet+/render-htmlworkflow used in academic-research production.
A curated, bilingual (中文 + English) collection of ML / LLM / multimodal / diffusion / agent / generative-model interview cheat sheets, auto-generated by the ARIS — Auto 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).
🌐 ARIS-Homepage preview — CV → fact-checked academic homepage (click to expand)📖 Preview (above): one snapshot per pillar, taken from the Diffusion Foundations cheat sheet — ① Foundations (formula derivations + intuition + TL;DR), ② Interview Q&A (25 high-frequency questions stratified L1/L2/L3), ③ From-Scratch Code (runnable PyTorch, including CFG training + DDIM sampling). Every cheat sheet in this collection follows the same three-pillar structure.
📱 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's New
- 2026-07-31 —
✂️ Interview-scannability overhaul for #30-33 + collection-wide table-scroll fix — responding to reader feedback ("comprehensive but unscannable before an interview"): Transformer Block restructured — the concrete block assembly + dataflow + runnable code moved from a buried §7 up to §1 (answer first, rationale after); all four de-hedged — lead sentence states the conclusion, qualifiers demoted to notes, one canonical home per caveat (inference visible prose -33.5%, transformer_block -17.2%, eval -17.4%), zero factual changes; a quantitative screen confirmed the older 29 tutorials healthy. Renderer wide-table overflow fixed, all 67 HTMLs re-rendered; all four EN editions retranslated + fidelity-reviewed. Gate PASS. (#37 · 28e4fb9)
- 2026-07-22 —
🧱 4 new cheat sheets (#30-33): Transformer Block · LLM Evaluation & Benchmarking · LLM Pretraining Pipeline · LLM Inference & Serving Stack — four foundational/systems topics in one batch: residual topologies & the MQA/GQA/MLA design axes, unbiased pass@k estimation & LLM-as-judge, Kaplan vs Chinchilla & the corpus-factory data pipeline, the request state machine & PagedAttention/KV lifecycle — 25-30 interview questions each. First batch to move the cross-model design review before drafting (90-105 numbered guardrails each), then 3-5 independent GPT-5.6-sol review batches; 3 real bugs were each caught independently by multiple batches (Bradley-Terry separation criterion, the best-of-n KV formula). All bilingual with runnable scripts, gate PASS. (#36 · 74644cf)
- 2026-07-13 —
- 2026-07-12 —
` ≥30 lines wrapped in `
`, per-block override via ` ```python {collapsed}` / `{open}` fence flags), paper citation popover (new `[[key]]` MD syntax + `--papers ` sidecar), eyebrow cleanup (marketing uppercase → body-serif gray), `--blog-mode` infrastructure (opt-in `aris-blog` body class). XSS-hardened script injection via `json_for_script()` (escapes `` break-out). All 23 bilingual tutorial pairs (= 46 HTMLs) regenerated to pick up the new template shell — source MDs untouched. Codex GPT-5.5 xhigh 4-round review (design × 2 → code × 1 → spot-check × 1). Try it: scroll [`attention_tutorial.html`](docs/tutorials/attention_tutorial.html) and watch the TOC sidebar follow ([b79c57d](https://github.com/wanshuiyin/ARIS-in-AI-Offer/commit/b79c57d), [8793f40](https://github.com/wanshuiyin/ARIS-in-AI-Offer/commit/8793f40)).
- **2026-05-26** —  🐍 **5 runnable PyTorch tutorial scripts** — first runnable-code contribution in [`docs/tutorials/code/`](docs/tutorials/code/): [`mha.py`](docs/tutorials/code/mha.py) (MHA + causal mask) · [`axial_attention.py`](docs/tutorials/code/axial_attention.py) (H/W axial + complexity table) · [`flow_matching.py`](docs/tutorials/code/flow_matching.py) (Rectified Flow on 2D moons) · [`mmdit_block.py`](docs/tutorials/code/mmdit_block.py) (double-stream MMDiT block) · [`toy_mmdit_t2i_pipeline.py`](docs/tutorials/code/toy_mmdit_t2i_pipeline.py) (end-to-end T2I skeleton). Pure PyTorch, CPU-runnable in seconds, every script ships with built-in `assert` sanity checks (shape parity, numerical agreement with `nn.MultiheadAttention` where applicable). Pairs with [`attention_tutorial.md`](docs/tutorials/attention_tutorial.md) / [`flow_matching_tutorial.md`](docs/tutorials/flow_matching_tutorial.md) / [`image_generation_systems_tutorial.md`](docs/tutorials/image_generation_systems_tutorial.md) ([f63f468](https://github.com/wanshuiyin/ARIS-in-AI-Offer/commit/f63f468)).
- **2026-05-24** —  🐙 **ARIS-Homepage v1.1: `--from-repos`** — snapshot user-selected `owner/repo` list via `gh` CLI; LLM agent merges repo timelines into homepage News + `featured_projects[].github`. Private repos skipped by default. Closes [#2](https://github.com/wanshuiyin/ARIS-in-AI-Offer/issues/2) by [@Yafei-Liu99](https://github.com/Yafei-Liu99) ([cdcf9a2](https://github.com/wanshuiyin/ARIS-in-AI-Offer/commit/cdcf9a2)).
- **2026-05-23** —  🌐 **ARIS-Homepage v1 shipped** — CV → fact-checked academic homepage (DBLP / arXiv audit blocks wrong venue / year / author). Single-file HTML; Codex / Gemini reviews optional. Live demo: [wanshuiyin.github.io](https://wanshuiyin.github.io/). Skill: [`skills/homepage-generator/SKILL.md`](skills/homepage-generator/SKILL.md) ([b818c1d](https://github.com/wanshuiyin/ARIS-in-AI-Offer/commit/b818c1d)).
- **2026-05-22** —  🦾 **Featured community contribution: 具身智能高频面试题库** by [@WinstonJQ](https://github.com/WinstonJQ) — 413 questions across 8 卷 (VLA / 模仿学习 / RL / 世界模型 / 工程落地 / 腿足控制 / 3D 感知 / 系统设计). Hosted externally; linked from the new "🦾 Embodied AI" category in the Tutorial Index ([b1ebb6f](https://github.com/wanshuiyin/ARIS-in-AI-Offer/commit/b1ebb6f)).
- **2026-05** —  📚 **4 new bilingual cheat sheets**: KL Divergence in RLHF (k1/k2/k3 · placement gradient bias), LLM On-Policy Distillation (MiniLLM / GKD / Qwen3 / Tinker), Diffusion Post-Training (DDPO / DPOK / DRaFT / AlignProp / Diffusion-DPO / Flow-GRPO), Diffusion / Flow Distillation (CM / iCT / sCM / CTM / LCM / DMD/DMD2 / ADD/LADD). Total now: **23 first-party cheat sheets**.
- **2026-05** —  📖 **README restructure** — preview-strip banner, ARIS credentials at top (badges + 10K-star foundation paragraph), shared WeChat community QR with the [main ARIS repo](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep).
---
## 📝 Blog Index
Long-form technical blogs — hand-authored, cross-model reviewed; outside the audited `/render-html` pipeline (figures © their original authors, used with attribution).
| Blog | What it covers | |
|---|---|---|
| **NVIDIA Cosmos 3 — MoT Architecture Deep-Dive** (中文) | Omnimodal world model · Mixture-of-Transformers · a walkthrough of the 138-page Cosmos 3 technical report | [📄 Read](https://wanshuiyin.github.io/ARIS-in-AI-Offer/blogs/cosmos3_mot_guide.html) |
| **A Survey on Continuous DLM — Representation Perspective** (中文) | Continuous diffusion language models through a representation lens · ELF / ByteDance Cola-DLM / Flow-Matching family (2026 H1) | [📄 Read](https://wanshuiyin.github.io/ARIS-in-AI-Offer/blogs/continuous_dlm_representation_perspective.html) |
| **Diffusion × Representation × Manifold** (中文) | The "borrow representation / use the manifold" threads in image & video diffusion · SSL / Consistency / REPA / RAE / JiT / V-JEPA2 · cross-referenced with the Continuous DLM survey | [📄 Read](https://wanshuiyin.github.io/ARIS-in-AI-Offer/blogs/diffusion_representation_manifold.html) |
---
## 📚 Tutorial Index
> 🌐 **Bilingual editions**: every cheat sheet ships with both a Chinese (default) and an English HTML — filenames are `*_tutorial.html` (CN) and `*_tutorial_en.html` (EN). HTML columns below link to both.
### 🧠 General / Foundations
| Topic | HTML 中文 | HTML EN | MD |
|---|---|---|---|
| **Attention Interview Cheat Sheet** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/attention_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/attention_tutorial_en.html) | [MD](docs/tutorials/attention_tutorial.md) |
| **Transformer Block (Post-LN/Pre-LN/branch pre+post residual topologies · MHA/MQA/GQA/MLA · Dense FFN vs MoE · GPT-2→Llama-style evolution)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/transformer_block_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/transformer_block_tutorial_en.html) | [MD](docs/tutorials/transformer_block_tutorial.md) |
| **LLM Evaluation & Benchmarking (pass@k unbiased estimation · evaluator ladder · benchmark contamination detection · LLM-as-judge · Bradley-Terry/Elo)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/llm_evaluation_benchmarking_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/llm_evaluation_benchmarking_tutorial_en.html) | [MD](docs/tutorials/llm_evaluation_benchmarking_tutorial.md) |
| **Normalization / Residual / Init (BatchNorm / LayerNorm / RMSNorm / Pre-vs-Post-LN / DeepNorm / QK-Norm / Xavier·Kaiming / μP)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/normalization_init_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/normalization_init_tutorial_en.html) | [MD](docs/tutorials/normalization_init_tutorial.md) |
| **Optimizers & LR Schedules (SGD·Momentum / Adam·AdamW / Muon·Lion·Shampoo·SOAP / warmup·cosine·WSD)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/optimizer_lr_schedule_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/optimizer_lr_schedule_tutorial_en.html) | [MD](docs/tutorials/optimizer_lr_schedule_tutorial.md) |
| **Tokenization (BPE / WordPiece / Unigram·SentencePiece / byte-level·byte fallback / vocab·fertility·BPB / tokenizer-free)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/tokenization_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/tokenization_tutorial_en.html) | [MD](docs/tutorials/tokenization_tutorial.md) |
| **KL Divergence in RLHF (k1/k2/k3 · placement gradient bias)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/kl_divergence_rlhf_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/kl_divergence_rlhf_tutorial_en.html) | [MD](docs/tutorials/kl_divergence_rlhf_tutorial.md) |
### 🎯 Post-Training & Reasoning
| Topic | HTML 中文 | HTML EN | MD |
|---|---|---|---|
| **RLHF / DPO / GRPO / PPO** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/rlhf_dpo_grpo_ppo_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/rlhf_dpo_grpo_ppo_tutorial_en.html) | [MD](docs/tutorials/rlhf_dpo_grpo_ppo_tutorial.md) |
| **Reasoning Models (o1 / R1 / Test-Time Compute / PRM)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/reasoning_models_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/reasoning_models_tutorial_en.html) | [MD](docs/tutorials/reasoning_models_tutorial.md) |
| **LLM On-Policy Distillation (MiniLLM / GKD / Qwen3 / Tinker)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/llm_opd_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/llm_opd_tutorial_en.html) | [MD](docs/tutorials/llm_opd_tutorial.md) |
| **LoRA / PEFT (LoRA / QLoRA / DoRA / rsLoRA / PiSSA / AdaLoRA / (IA)³)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/lora_peft_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/lora_peft_tutorial_en.html) | [MD](docs/tutorials/lora_peft_tutorial.md) |
### 🏛️ LLM Architecture & Systems
| Topic | HTML 中文 | HTML EN | MD |
|---|---|---|---|
| **MoE (DeepSeek-V3 / Mixtral / Llama 4)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/moe_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/moe_tutorial_en.html) | [MD](docs/tutorials/moe_tutorial.md) |
| **Long Context (RoPE / YaRN / NTK / MLA / StreamingLLM)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/long_context_rope_yarn_mla_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/long_context_rope_yarn_mla_tutorial_en.html) | [MD](docs/tutorials/long_context_rope_yarn_mla_tutorial.md) |
| **Linear / Sparse Attention (Linear Attn / SSM·Mamba / Mamba-2·SSD / DeltaNet / NSA·MoBA / Hybrid)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/linear_sparse_attention_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/linear_sparse_attention_tutorial_en.html) | [MD](docs/tutorials/linear_sparse_attention_tutorial.md) |
| **KV Cache + Speculative Decoding (Medusa / EAGLE / MLA)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/kv_cache_speculative_decoding_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/kv_cache_speculative_decoding_tutorial_en.html) | [MD](docs/tutorials/kv_cache_speculative_decoding_tutorial.md) |
| **Quantization (GPTQ / AWQ / FP8 / NVFP4 / SmoothQuant)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/quantization_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/quantization_tutorial_en.html) | [MD](docs/tutorials/quantization_tutorial.md) |
| **Distributed Training (DDP / FSDP2 / ZeRO / TP / PP / EP / SP)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/distributed_training_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/distributed_training_tutorial_en.html) | [MD](docs/tutorials/distributed_training_tutorial.md) |
| **LLM Pretraining Pipeline (Kaplan vs Chinchilla scaling laws · corpus-factory data pipeline · document packing/loss masking · checkpoint resume)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/llm_pretraining_pipeline_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/llm_pretraining_pipeline_tutorial_en.html) | [MD](docs/tutorials/llm_pretraining_pipeline_tutorial.md) |
| **LLM Inference & Serving Stack (request state machine · exact sampling-operator definitions · PagedAttention/KV lifecycle · continuous batching/chunked prefill · disaggregation)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/llm_inference_serving_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/llm_inference_serving_tutorial_en.html) | [MD](docs/tutorials/llm_inference_serving_tutorial.md) |
### 🌊 Generative Models — Theory & Tokenizers
| Topic | HTML 中文 | HTML EN | MD |
|---|---|---|---|
| **Flow Matching Quick Reference** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/flow_matching_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/flow_matching_tutorial_en.html) | [MD](docs/tutorials/flow_matching_tutorial.md) |
| **Diffusion Foundations (DDPM / Score / DDIM / EDM / CFG)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/diffusion_foundations_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/diffusion_foundations_tutorial_en.html) | [MD](docs/tutorials/diffusion_foundations_tutorial.md) |
| **VAE / VQ-VAE / VQ-GAN / FSQ** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/vae_vqvae_vqgan_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/vae_vqvae_vqgan_tutorial_en.html) | [MD](docs/tutorials/vae_vqvae_vqgan_tutorial.md) |
### 🎨 Generation Systems — Image / Video / 3D / Diffusion Post-Training
| Topic | HTML 中文 | HTML EN | MD |
|---|---|---|---|
| **Image Gen Systems (LDM / SD / SDXL / SD3 / FLUX / ControlNet)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/image_generation_systems_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/image_generation_systems_tutorial_en.html) | [MD](docs/tutorials/image_generation_systems_tutorial.md) |
| **Video Gen (Sora / Hunyuan-Video / Kling / Wan / Movie Gen)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/video_generation_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/video_generation_tutorial_en.html) | [MD](docs/tutorials/video_generation_tutorial.md) |
| **3D Gen (NeRF / Instant-NGP / 3DGS / SDS / Trellis)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/3d_generation_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/3d_generation_tutorial_en.html) | [MD](docs/tutorials/3d_generation_tutorial.md) |
| **Diffusion Post-Training (DDPO / DPOK / DRaFT / AlignProp / Diffusion-DPO / Flow-GRPO)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/diffusion_post_training_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/diffusion_post_training_tutorial_en.html) | [MD](docs/tutorials/diffusion_post_training_tutorial.md) |
| **Diffusion / Flow Distillation (CM / iCT / sCM / CTM / LCM / DMD/DMD2 / ADD/LADD)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/diffusion_distillation_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/diffusion_distillation_tutorial_en.html) | [MD](docs/tutorials/diffusion_distillation_tutorial.md) |
### 👁️ Multimodal
| Topic | HTML 中文 | HTML EN | MD |
|---|---|---|---|
| **VLM (CLIP / LLaVA / Qwen-VL / DeepSeek-VL)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/vlm_multimodal_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/vlm_multimodal_tutorial_en.html) | [MD](docs/tutorials/vlm_multimodal_tutorial.md) |
### 🤖 Agents
| Topic | HTML 中文 | HTML EN | MD |
|---|---|---|---|
| **Agent Foundations (ReAct / MCP / A2A / SWE-bench / GAIA / OSWorld)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/agent_foundations_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/agent_foundations_tutorial_en.html) | [MD](docs/tutorials/agent_foundations_tutorial.md) |
| **Agentic RL (AgentTuning / ToolRL / RAGEN / WebRL / SWE-RL / GRPO for tool use)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/agentic_rl_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/agentic_rl_tutorial_en.html) | [MD](docs/tutorials/agentic_rl_tutorial.md) |
| **Multi-Agent & Long-Horizon (CAMEL / AutoGen / MetaGPT / MoA / Debate / MemGPT / LATS)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/multi_agent_long_horizon_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/multi_agent_long_horizon_tutorial_en.html) | [MD](docs/tutorials/multi_agent_long_horizon_tutorial.md) |
| **Self-Evolving Agents (Ctx2Skill / Native Evolution / A²RD / Voyager / Reflexion / STaR)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/self_evolving_agents_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/self_evolving_agents_tutorial_en.html) | [MD](docs/tutorials/self_evolving_agents_tutorial.md) |
| **RAG + Embedding / Retrieval (InfoNCE / 难负例 / Matryoshka / BM25 / RRF / ColBERT / GraphRAG)** | [📄 CN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/rag_embedding_retrieval_tutorial.html) | [📄 EN](https://wanshuiyin.github.io/ARIS-in-AI-Offer/tutorials/rag_embedding_retrieval_tutorial_en.html) | [MD](docs/tutorials/rag_embedding_retrieval_tutorial.md) |
> 🎉 **23 tutorials live (bilingual)** (2026-05) — each ships with both Chinese and English HTML. Seven buckets: General · Post-Training · Architecture · Generative · Multimodal · Agents · Diffusion Post-Training. This round adds 4 new sheets: KL Divergence in RLHF, LLM On-Policy Distillation, Diffusion Post-Training, Diffusion Distillation. More (Flow-OPD / Audio Gen / further SOTA updates) coming — **PRs welcome** (see [CONTRIBUTING](CONTRIBUTING.md)).
### 🦾 Embodied AI / 具身智能
> 🌟 **Community contribution** by [@WinstonJQ](https://github.com/WinstonJQ) — hosted externally on a separate repo, generously shared with the community. If it helps your interview prep, please ⭐ the source repo to thank the author 🙏
| Topic | HTML 中文 | Source |
|---|---|---|
| **具身智能高频面试题库** (VLA / 模仿学习 / RL / 世界模型 / 工程落地 / 腿足控制 / 3D 感知 / LeetCode·系统设计 — 413 题，8 卷) | [📄 CN (online)](https://winstonjq.github.io/embodied-interview-qa/) | [@WinstonJQ/embodied-interview-qa](https://github.com/WinstonJQ/embodied-interview-qa) |
---
## 🤖 How These Are Generated
Every tutorial uses [ARIS](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)'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** — trajectory-based; keep going if FAIL set is shrinking, stop if same issue recurs or ~6 rounds without convergence
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.
---
## 🌐 ARIS-Homepage — fact-checked academic homepage from CV
> **The only personal-site generator that fact-checks your CV before publishing.**
A new skill in this repo: `/homepage-generator` turns your CV (`.docx` / `.pdf` / `.txt`) into a polished single-file academic homepage. Cross-model factual audit runs against DBLP / arXiv — wrong venue / year / author / fabricated awards block ship until corrected or explicitly overridden.
**Live demo**: [wanshuiyin.github.io](https://wanshuiyin.github.io/) — generated by this skill from a CV + the maintainer's previous manual page as editorial reference. Preview strip is near the top of this README.
### Quick start
aris-homepage init --from-cv ./cv.pdf --out ./site
cd ./site
# Calling agent fills .aris-homepage/extraction.json per EXTRACTION_HANDOFF.md
aris-homepage finalize
$EDITOR profile.yml # tweak editorial choices
aris-homepage render --persona theory-minimal
Output: `index.html` + `audit-report.md`. Drop the HTML on GitHub Pages, S3, university `~user/public_html/`, or attach to email — no build server. **Minimum runtime is just Python + a calling LLM agent**; Codex MCP optional for adversarial cross-model review; Gemini multimodal optional for visual critique.
### How it works
ARIS-Homepage Pipeline
📄 CV (.docx/.pdf/.txt) 🌐 Manual Homepage URL 🖼 Assets Dir
factual source editorial (optional) visual (opt.)
│ │ │
▼ │ │
┌──────────┐ │ │
│ init │ │ │
│ extract │ │ │
│ CV→text │ │ │
└─────┬────┘ │ │
▼ ▼ ▼
┌─────────────────────────────────────────────────────────────────┐
│ 🤖 Calling LLM agent reads EXTRACTION_HANDOFF.md + │
│ optional manual-homepage URL + assets dir as context │
│ → writes .aris-homepage/extraction.json │
└─────────────────────────┬───────────────────────────────────────┘
▼
┌──────────┐
│ finalize │
└─────┬────┘
▼
┌─────────────────────────────────────────────────────────────────┐
│ ✋ Editable source files (truth lives here, edit in IDE): │
│ profile.yml · publications.bib · bio.md · news.md │
│ EXTRACTION_REVIEW.md (review LLM uncertain extractions) │
└─────────────────────────┬───────────────────────────────────────┘
▼
┌────────────────────────┐
│ render │
│ --persona │
│ theory-minimal │
└───────────┬────────────┘
│
┌───────────────┼───────────────┐
▼ ▼ ▼
┌──────────┐ ┌──────────┐ ┌──────────────┐
│ Layer-1 │ │ Layer-2 │ │ Layer-2 │
│ DBLP / │ │ Codex MCP│ │ Gemini │
│ arXiv │ │ adv-rev │ │ visual │
│ fact-chk │ │ (opt.) │ │ critique │
│ (always) │ │ │ │ (opt.) │
└─────┬────┘ └──────────┘ └──────────────┘
│
▼
┌──────────────┐
│ index.html + │
│ audit-report │ ──▶ 🚀 Deploy: GitHub Pages · S3 · email · anywhere
│ .md │
└──────────────┘
Typical flow (7 steps, ~5 minutes):
1. aris-homepage init --from-cv ./cv.pdf --out ./site
2. (calling agent) read .aris-homepage/EXTRACTION_HANDOFF.md
→ fill .aris-homepage/extraction.json
3. aris-homepage finalize
4. $EDITOR profile.yml publications.bib bio.md news.md
5. aris-homepage check --strict # fact-check only
6. aris-homepage render --persona theory-minimal
7. inspect audit-report.md; fix → re-render OR --override-all
Minimum runtime: Python + a calling LLM agent.
Codex MCP optional (cross-model adversarial review).
Gemini optional (multimodal visual critique).
- **Skill contract**: [`skills/homepage-generator/SKILL.md`](skills/homepage-generator/SKILL.md)
- **Complete schema**: [`skills/homepage-generator/PROFILE_SCHEMA.md`](skills/homepage-generator/PROFILE_SCHEMA.md)
- **Implementation**: [`tools/aris_homepage.py`](tools/aris_homepage.py) (pure-stdlib Python; `pip install pyyaml` away from working)
- **Template**: [`tools/templates/homepage-theory-minimal.html`](tools/templates/homepage-theory-minimal.html)
---
## 🤝 Contributing
One person can only cover so much. The hope is that many hands make this collection more complete.
Full contribution guide: [**CONTRIBUTING.md**](CONTRIBUTING.md) ([English](CONTRIBUTING.md) · [中文](CONTRIBUTING_CN.md)) — covers ARIS workflow invocation, strict style guide (headings / math / tables / callouts / personal-info banlist), and PR checklist.
**TL;DR**: use the [`/interview-cheatsheet`](skills/interview-cheatsheet/SKILL.md) + [`/render-html`](skills/render-html/SKILL.md) workflow to generate, then open a PR. Both skills enforce a cross-model codex GPT-5.5 xhigh review gate (math / code / citation / render fidelity), so anything merged via PR has a baseline quality floor. Skill source and `tools/render_html.py` are bundled in this repo so you can fork & extend.
**Honest disclaimer**: across the existing tutorials, the HTML structural foundations (math, code, tables, callouts, TOC, responsive layout) are solid. But the very latest frontier work in any given topic (e.g., methods released in late 2025, niche subfield updates) likely is not fully covered. If you spot something outdated or wrong, PRs and issues are equally welcome — let's keep this resource alive together.
---
## 💬 Community
**Shared community with the main [ARIS repo](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)** — the same WeChat group covers ARIS skill workflows + this tutorial collection. Join to discuss interview prep, request new cheat-sheet topics, or share corrections / contributions:
### 🔭 Community Showcase
Community-built projects derived from this collection (MIT license — attribution-preserving reuse welcome):
- **[大模型秋招教程 (ARIS-in-AI-Offer & Hello-Agents)](https://qizishi.github.io/Autumn-Recruitment-Tutorials-for-LLM/)** by [@QiZishi](https://github.com/QiZishi) — an online reading index that merges all 23 Chinese tutorials here with [Datawhale Hello-Agents](https://github.com/datawhalechina/hello-agents)' LLM interview Q&A, organized as clickable tutorial cards ([repo](https://github.com/QiZishi/Autumn-Recruitment-Tutorials-for-LLM) · from [#3](https://github.com/wanshuiyin/ARIS-in-AI-Offer/issues/3)).
Built something on top of these tutorials? Open an issue and we'll list it here.
---
## 🌟 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.
[](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/stargazers) · [](https://huggingface.co/papers/2605.03042) · [](https://huggingface.co/papers/2605.03042) · [](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep) · [](https://github.com/VoltAgent/awesome-agent-skills) · [](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
---
## 📖 Citing ARIS
If this collection — or any cheat sheet here — helped you in your interview prep / research / paper, please consider citing the underlying ARIS methodology paper:
@article{yang2026aris,
title={ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration},
author={Yang, Ruofeng and Li, Yongcan and Li, Shuai},
journal={arXiv preprint arXiv:2605.03042},
year={2026}
}
Every tutorial in this repo was generated end-to-end by the ARIS `/interview-cheatsheet` + `/render-html` workflow with cross-model adversarial review (Claude × GPT-5.5 xhigh × Gemini). The citation supports the methodology behind the workflow, not just this collection.
---
## License
[MIT](LICENSE) — use, modify, share, fork freely. Hope this helps your job search. 💪