SIGRobotics Docs

This repo contains documentation and references that can be used to learn a lot of the most popular robot learning topics.

The papers/resources within each topic are roughly organized by date, so you can easily follow the development of each topic over time

Table Of Contents

• Background Info (math and ML basics)
• Introduction to Classical Robotics
• Computer Vision
• Generative Models
• Large Language Models (LLMs)
• Vision-Language-Action Models
• Reinforcement Learning
• World Models

Background Info

Back to Top

Probability Theory

• Cheat Sheet
• Deeper Dive on Random Variables

Linear Algebra

• General Lin Alg Review
• Applied Lin Alg
• Lin Alg for ML

Optimization Methods

• Numerical Optimization
• Optimization for ML

Machine Learning Basics

• General ML Reference (Very Long)
• ML Basics
• Perceptrons
• Convolutional Neural Networks (CNNs)
• Recurrent Neural Networks (RNNs)

Classical Robotics

Back to Top

Controls

• Proportional-Integral-Derivative (PID) Control
• Linear-Quadratic Regulator (LQR)
• Model Predictive Control (MPC)

Path Planning

• Graph Searches, A*, RRT/RRG (Chapter 7, starts on page 67)

State Estimation

• Kalman Filter
• Extended Kalman Filter
• Unscented Kalman Filter
• Particle Filter Algorithm
• Particle Filter Derivation/Math
• Simultaneous Localization and Mapping (SLAM)

System Modeling

• State Space Modeling
• Transfer Functions, Frequency Domain Modeling
• System Identification (Deep Dive)
• Frequency Domain System Identification

Classical CV

• Pinhole Camera Model
• Camera Calibration
• Stereo Depth Estimation

Computer Vision

Back to Top

Initial CNNs

• AlexNet (2012)
• GoogLeNet (2014)
• ResNet (2015)
• U-Net (2015)
• DenseNet (2016)

Yolo

• YOLOv1 (2016)
• YOLOv8 (2023)
• YOLOv11 (2024)
• YOLOv26 (2025)

Dino

• DINO (2021)
• DINOv2 (2023)
• DINOv3 (2025)

CLIP

• CLIP (2021)

Generative Models

Back to Top

VAE

• VAE Tutorial (2019)
• Variational Autoencoders (2013)
• VQ-VAE (2017)

Diffusion Models

• Diffusion Tutorial (2022)
• Diffusion Tutorial (2024)
• Diffusion From Thermodynamics (2015)
• Score-Based Diffusion (2020)
• Denoising Diffusion (2020)
• Classifier Guidance (2021)
• Latent Diffusion (2022)
• Diffusion Policy (2023)
• Diffusion Posterior Sampling (2023)

Flow Matching

• Flow Tutorial (2025)
• Flow Matching (2022)
• Rectified Flow (2022)

Large Language Models (LLMs)

Back to Top

• Transformers (2017)
• BERT (2018)
• GPT (2018)
• GPT-2 (2019)
• T5 (2020)
• GPT-3 (2020)
• Scaling Laws (2021)
• Instruction Tuning (2021)
• RLHF (2022)
• Flash Attention (2022)
• LLaMA (2023)
• Mixture of Experts (2024)

Vision-Language-Action Models

Back to Top

Vision-Language Models (VLMs)

• ALIGN (2021)
• CLIP (2021)
• SimVLM (2021)
• BLIP (2022)
• Flamingo (2022)
• CoCa (2022)
• PaLI (2022)
• PaLM-E (2023)
• LLaVA (2023)
• BLIP-2 (2023)
• GPT-4V (2023)
• Qwen2.5-VL (2025)

Vision-Language-Action Models (VLAs)

• RT-1 (2022)
• PaLM-E (2023)
• RT-2 (2023)
• Open X-Embodiment (2023)
• OpenVLA (2024)
• pi0 (2024)
• pi0.5 (2025)
• FAST (2025)
• GROOT-N1 (2025)
• pi0.6 (2025)
• pi0.7 (2026)
• GROOT-Dreamer (2026)

Reinforcement Learning

Back to Top

• Temporal Difference (1988)
• Q-Learning (1989)
• Policy Gradient (1992)
• REINFORCE (1999)
• Deep Q-Network (2013)
• Double Deep Q-Network (2015)
• Trust Region Policy Optimization (2015)
• Asynchronous Advantage Actor-Critic (2016)
• Deep Deterministic Policy Gradient (2016)
• Proximal Policy Optimization (2017)
• Soft Actor-Critic (2018)
• MuZero (2019)
• Decision Transformer (2021)
• Direct Preference Optimization (2023)

World Models

Back to Top

• World Models (2018)
• PlaNet (2018)
• Dreamer (2019)
• DreamerV2 (2020)
• DreamerV3 (2022)
• IRIS (2022)
• Genie (2022)
• Genie 2 (2023)
• V-JEPA (2023)
• Sora (2024)
• Cosmos (2025)