---
layout: farshid_default
title: "Sitemap & Page Summaries"
permalink: /notes/sitemap/
description: "Complete navigation index with summaries of all site pages"
markmap: |
  # Sitemap
  ## Product
  - Computer Vision
  - AI & LLMs
  - CUDA & GPU
  ## Solution
  - Courses
  - Business
  ## Atlas
  - About
  - Research
  - Programming
  - Optimization
  - Knowledge
---

Complete navigation index with summaries of all site pages

*Last updated: 2026-09-04.*  <!--ENHANCED-->
# Sitemap — All Pages

## Product

### Computer Vision
- **[3D Vision & Multi-Camera](/notes/docs/cv/3d/)** — Real-time 3D point cloud generation, depth sensing, multi-camera sync with OpenCV, GStreamer, and C++
- **[Optical Flow](/notes/docs/cv/optical-flow/)** — Challenges and solutions: illumination, occlusions, fast motion, textureless regions, GPU acceleration
- **[Multi-Camera Systems](/notes/docs/cv/multi-camera/)** — Architecture guide for scaling to 100+ cameras: sync, GPU/NPU, USB/DMA
- **[CV Overview](/notes/docs/cv-overview/)** — Computer vision research and overview
- **[CV Coaching](/notes/docs/coaching/)** — Computer vision teaching and coaching services

### AI & LLMs
- **[Advanced LLM Concepts](/notes/docs/llm/llm-concepts/)** — RAG, embeddings, knowledge graphs, multimodal models, production deployment
- **[Orchestrating Agents](/notes/docs/llm/agents/)** — Multi-agent systems, task decomposition, LLM orchestration
- **[Blog: AI & LLMs](/notes/docs/llm/blog/)** — RAG vs CAG, multi-agent architectures, AI's impact
- **[Avatar Generator](/notes/docs/llm/avatar/)** — Local video avatar with Ollama + Wav2Lip (no cloud)
- **[Local LLM Optimization](/notes/docs/llm/local-llm-optimization/)** — Fastest Qwen3.5 at 64K context on Apple M3 via MLX (oMLX/llama.cpp), with downloadable scripts
- **[K2-Horizon Locally](/notes/docs/llm/k2-horizon-local/)** — Serve IFM K2-Horizon GGUF via the MBZUAI-IFM llama.cpp fork on Apple Silicon, wired into Hermes at 64K

### CUDA & GPU
- **[Numba JIT](/notes/docs/cuda/numba/)** — Python 10-100x speedup with @jit(nopython=True)
- **[PyCUDA Kernels](/notes/docs/cuda/pycuda/)** — CUDA C kernels from Python with GPU memory management
- **[CUDA in VS Code](/notes/docs/cuda/cuda-vscode/)** — Dev environment setup on Windows
- **[MLX, CoreML & Metal](/notes/docs/cuda/apple-ml/)** — Apple Silicon ML frameworks

---

## Solution

### Courses
- **[All Topics](/notes/courses/)** — Complete topics index
- **[ML Specialization](/notes/courses/ml-spec/)** — Coursera ML notes
- **[Full Stack DL](/notes/courses/fsdl/)** — ML production, data lifecycle
- **[FSDL 2022](/notes/courses/fsdl-2022/)** — Continual learning, data management, testing
- **[MLOps](/notes/courses/mlops/)** — ML engineering for production
- **[ROS](/notes/courses/ros/)** — Robot Operating System
- **[Parallel Programming](/notes/courses/parallel/)** — Python parallel CV
- **[Modern C++](/notes/courses/modern-cpp/)** — C++29 for image processing
- **[Cloud-Native](/notes/courses/cloud-native/)** — Docker & Kubernetes
- **[TF Deployment](/notes/courses/tf-deploy/)** — TF.js, TF Lite, mobile ML
- **[RISC-V](/notes/courses/risc-v/)** — Open-source processor architecture
- **[Edge AI Summit](/notes/courses/edge-ai-summit/)** — TinyML, neuromorphic, edge inference
- **[Embedded IoT](/notes/courses/iot/)** — Embedded systems
- **[Tesla AI](/notes/courses/tesla/)** — Autonomous driving
- **[AI Hardware](/notes/courses/ai-hardware/)** — Accelerators & NPUs
- **[OpenVINO](/notes/courses/openvino/)** — Intel inference optimization
- **[Metaverse](/notes/courses/metaverse/)** — XR & spatial computing
- **[Book Summaries](/notes/courses/book-summary/)** — Knowledge management, PKM
- **[IoT Scholarship](/notes/courses/iot-scholarship/)** — OpenVINO edge AI, object detection

### Business
- **[Startup Guide](/notes/docs/startup/)** — Edge AI business plans, fundraising in Germany, pitch decks
- **[SEO for LLMs](/notes/docs/seo/)** — Structured data, AI-friendly content optimization
- **[Top LinkedIn Posts](/notes/docs/linkedin/)** — Top posts: camera calibration, C++, robotics
- **[10 Years of Bug Fixing](/notes/pubs/10-years/)** — Lessons from fixing bugs in CV systems
- **[Solutions](/notes/docs/solutions/)** — Industry solutions and business
- **[Connect](/notes/docs/solutions/#connect)** — Get in touch

---

## Atlas

### About
- **[Crypto](/farshid/content/crypto.md)** — Support the site with crypto donations (ETH, BTC, SOL, Base, BNB)
- **[MetaMask](/farshid/content/metamask.md)** — Connect a crypto wallet and test send/receive
- **[Game](/farshid/content/game.md)** — Play Snake, Flappy Bird and 2048 in your browser
- **[QR Codes](/farshid/content/qr.md)** — Scan QR codes to open referral & join links (OpenCode, Trade Republic, Scalable, Wise, eToro)
- **[Solana Games](/farshid/content/solana-games.md)** — Simple Solana games and on-chain mini-games
- **[Shop](/shop/)** — Digital downloads: branded PDF guides and ebooks
- **[Book](/book/)** — Computer Vision & AI Engineer's Guide (free PDF)

### Research
- **[Patents](/notes/pubs/patents/)** — 3 patents: face augmentation, vehicle detection, facial analysis
- **[Papers](/notes/pubs/papers/)** — 11 conference papers: camera calibration, license plates, thresholding
- **[Journals](/notes/pubs/journals/)** — 6 journals: PSNR, SLAM, ant colony, character recognition
- **[Books](/notes/pubs/books/)** — 7 books: optical flow, camera calibration, OpenCV 5 chapters, CV meets LLM
- **[Keynotes](/notes/pubs/keynotes/)** — LLMs meet Computer Vision
- **[CV](/notes/pubs/cv/)** — Full curriculum vitae

### Programming
- **[C++ Reference](/notes/docs/cpp/)** — Memory (stack/heap), STL, debugging, Linux essentials
- **[Python Config](/notes/docs/python/)** — ConfigParser, argparse, pydantic, hydra, pybind11, Cython
- **[Developer Tools](/notes/docs/dev-tools/)** — Docker, GitHub tricks, CLI tools
- **[Shell & Vim](/notes/docs/shell-vim/)** — Terminal essentials, vim basics

### Optimization
- **[CV/DL/ML Optimization](/notes/docs/optimization/)** — Quantization, pruning, TensorRT, ONNX, frameworks
- **[Prompts](/notes/docs/prompts/)** — Reusable LLM prompt templates

### Knowledge
- **[Wiki](/notes/wiki/)** — Wikipedia-style index of all pages
- **[Sitemap](/notes/sitemap/)** — Complete page listing
- **[Presentations](/notes/slides/)** — All research-tool decks
  - **[The New Era of Research Tools](/notes/slides/research-tools/)** — Passive chat → autonomous workflows: Hermes, LeapSpace, PaperBanana, citation finders, swarms
  - **[New LLM Optimization Methods](/notes/slides/llm-optimization/)** — Unsloth Dynamic 3.0, MTP, DFlash2, oMLX/MLX, FlashAttention-2; Qwen3.8-Flash synthesis
  - **[Hermes for Research Assistance](/notes/slides/presentation/)** — Literature sweeps, code reproduction, paper drafting
  - **[Hermes for Big CV Projects](/notes/slides/presentation-cv/)** — Production-scale CV engineering with agents
  - **[Hermes Updates & Feature Guide](/notes/slides/presentation-updates/)** — Complete feature tour with examples
- **[Portfolio](/notes/pkm/use-cases/)** — Publications, patents, books, journals, papers, keynotes
- **[Resources](/notes/docs/resources/)** — Patents, books, papers, projects
- **[Curated Links](/notes/docs/links/)** — Tools, tutorials, reading, YouTube
- **[Content Hub](/notes/docs/)** — All content categories
