Knowledge Map
- 🧊 Pretty things here
- We model the world mathematically via different philosophical viewpoints
- 📍 Kaiming He, GDM
- Lukas Beyer’s blog, ex-GDM
- 📍 Yoshua Bengio, GAN 2014, DL
- 📍 Pedro Domingos
- Bernhard Schölkopf, SSL 2006
- Choice Overload – How Having Too Many Options Can Shut Down Your Brain
- Richard Feynman, Feynman: How to think 1 of 2 fun to Imagine 11
- How Multitasking Drains Your Brain
- Rust everything - blogs - Zurich
- time zone - (UTC+01:00) Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna
Model Structures
- 📍 Introduction to Flow Matching and Diffusion Models - MIT 25/26
- Flow-matching
- 2025 - Advances in Computer Vision
- 2026 - Implement your AI Model Experiments
- 2026 - Ice Maze RL Basis
- ml-switcheroo
- 2025 - Mastering Learning Rate Schedulers in Deep Learning
- 2026 - Understanding Rust’s Memory Model
2025 - 2026
- Paul Graham, his website
- Prof. Davide Scaramuzza - UZH MS AI - Program Director
- (Prof. Andreas Geiger)
- (Prof. Sergey Tomin)
- (Dragomir Anguelov, Amirabbas Asadi)
- Max Welling
- DailyPapers
- Peyman Milanfar
- (Jurgen Schmidhuber)
- (Lawrence Jackel)
- 6G Communication
- Daily News Briefing, Reuters and CNBC
- Nicholas Carlini’s blog
Home / Hospital Robots
- Mehul Nariyawala
- 2026 - SLAM Handbook, chapter 17, 18
- 2016 - Dynamic SLAM
Readings
- [⛱️ Daily Finance Markets, Luca Lacharlotte]
- 2025 - Kosmos - AI Co-Scientist
- 2025 - Blackwell NVFP4 Kernel Hackathon
- [Armadillo]
- PRS
♨️ Zurich
Relevant Coursework
Deep Learning (Python, 25)
(*Large-Scale AI Engineering, 25/26)
Systems on Chips (CUDA, HPC, 26)
3D Shape Modeling and Geometry Processing (C++, 26)
Computational Models of Motion (C++ / Rust, Deep RL, Robotics, 26)
Computer Vision for Automated Driving / Future Mobility (PRS, 26)
4D Computer Vision (C++, (Dynamic) SLAM, 26)
Visual Computing
(Physically Based Simulation)
Doctoral Seminar in Visual Computing
(Vision Algorithms for Mobile Robotics (L+E))
Mixed Reality (C++, Blender, SUMO, Unreal, 25)
Graph Theory
Information Geometry
Pure Math
Post-Training Techniques
❄️ Efficient Adaptation
- Adapter (reduce training parameters)
- Distillation (transfer knowledge)
- Pruning (delete redundant structure)
❄️ Representation Learning
- Self-Supervised Learning - SSL
❄️ Model Manipulation
- Model Editing
- Model Merging
❄️ Generalization
- Few-shot Learning
- Zero-shot Learning
Check List
- Reading, Oxygen, Fruits No sugar, Protein
- Gym, Jogging, Tennis
- Chatting
- 🌊 Water
- Take a Walk 🗣️
Enjoy Reading This Article?
Here are some more articles you might like to read next: