In this repo, I save notes of papers, books, blogs, etc I read and found interesting. Most of them were recommended to read.
All the articles I've read and plan to read.
- Complexity of Planning with Partial Observability
- An introduction to Reinforcement Learning and its video
- World Models
- Gans and its analysis
- Learn more about (finite) MDPs
- Outracing champion Gran Turismo drivers with deep reinforcement learning
- Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot
- Improving Intrinsic Exploration with Language Abstractions
- Exploration via Elliptical Episodic Bonuses and OpenReview
- Accelerated Quality-Diversity through Massive Parallelism
- Discovering and Exploiting Sparse Rewards in a Learned Behavior Space
- Sparse Reward Exploration via Novelty Search and Emitters
- Emergence of Spatial Coordinates via Exploration
- Generalization in Cooperative Multi-Agent Systems
- (MuZero) Mastering Atari, Go, chess and shogi by planning with a learned model📝
- (AlphaZero) Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm📝
- (AlphaGo Zero) Mastering the game of Go without human knowledge📝
- (AlphaGO) Mastering the game of GO with deep neural networks and tree search📝
- (AlphaFold) Mastering the game of GO with deep neural networks and tree search📝
- (AlphaTensor) Discovering faster matrix multiplication algorithms with Reinforcement Learning📝
- (AlphaFold) Highly accurate protein structure prediction with AlphaFold📝
- (DeepNash) Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning📝
- ETA Prediction with Graph Neural Networks in Google Maps📝
- Reward is enough📝
- (30u30) Recurrent Neural Network Regularization📝
- (30u30) Keeping Neural Networks Simple by Minimizing the Description Length of the Weights📝
- (30u30) ImageNet Classification with Deep Convolutional Neural Networks📝
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction📝
- Test-Time Training with Masked Autoencoders
- Are Generative Classifiers More Robust to Adversarial Attacks?
- Integer tokenization is insane📝
- DeepSeekMath📝
- LLaDA📝
- Pangy: Accurate medium-range global weather forecasting with 3D neural networks
- GraphCast: Learning skilful medium-range global weather forecasting📝
- GenCast: Diffusion-based ensemble forecasting for medium-range weather📝
- ArchesWeather & ArchesWeatherGen: A Deterministic and Generative Model for ML Weather Forecasting
- Neural GCM: Neural General Circulation Models for Weather and Climate📝
- Aurora: A Foundation Model for the Earth System📝
- Writing a research article: advice to beginners📝
- How to do Research At the MIT AI Lab
- Writing a Good Research Paper by Vincent Lepetit
- How to write a great research paper: Slides and Video by Simon Peyton Jones
- How to give a great research talk: Slides, Video and Paper
- How to give a talk and write a paper (last slides): Slides by Ivan Laptev
- Ten Simple Rules for Mathematical Writing: Web page by Dimitri P. Bertsekas
- What's wrong with these equations?: PDF by David Mermin
- Notes on Technical Writing: PDF by Don Knuth
- How to Get Your SIGGRAPH Paper Rejected: PDF by Jim Kajiya
- How to write a good research paper: Slides by Bill Freeman
- Writing papers and giving talks: Slides by Bill Freeman
- Pointers on giving a talk: Web site by David G. Messerschmitt
- Navigating the Ph.D. Odyssey: A Resource Toolkit by Amar Meddahi
- Flow Matching Guide and Code
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- Perceiver IO: A General Architecture for Structured Inputs & Outputs
- Ilya 30u30 (5/30) by Ilya Sutskever
- Making the World Differentiable
- Player of Games
- Approximate exploitability: Learning a best response in large games
- Towards a Better Understanding of Representation Dynamics under TD-learning
- Deep reinforcement learning with double q-learning
- The road to modern AI
- Reinforcement Learning from Human Feedback
- (30u30) RNNs and LSTMS notes📝
- (30u30) The first law of complexodynamics📝
Author: Scott Aaronson - (Event - CDF) AI and Math for Meteorology and Climatology📝
Here are some books I keep somewhere if needed:
- Is Parallel Programming Hard, And, If So, What Can You Do About It? by Paul McKenney
- Deep Learning - Foundations and Concepts by Christopher Bishop
- Pattern recognition and machine learning by Christopher Bishop
- Software Engineering at Google and the book in short SWE at Google in short
- Deep Learning with Python by François Chollet
- The Book of Statistical Proofs by Joram Soch et al.
- Statistical Learning and Sequential Prediction by Karthik Sridharan and Sasha Rakhlin
- Algorithms for Optimizations/Decision making by Mykel J. Kochenderfer, Tim A. Wheeler and Kyle H. Wray
- An introduction to Reinforcement Learning by Richard S. Sutton and Andrew G. Barto
- Advances in Financial Machine Learning by Marcos López de Prado
- Deep Learning by Ian GoodFellow
Here are some blogs, videos or webpages that I found interseting:
- About GPUs and CUDA/PyTorch: The ultrascale-playbook and Visualize and understand GPU memory in PyTorch
- About processing and evaluating data quality at scale: 🍷 FineWeb: decanting the web for the finest text data at scale
- AI Seminar Series by M. Debbah
- CONFERENCE JENSEN HUANG (NVIDIA) and ILYA SUTSKEVER (OPEN AI): AI TODAY AND VISION OF THE FUTURE📝 by Ilya Sutskever and Jensen Huang
- Quality-Diversity optimisation algorithms by Antoine Cully, Jean-Baptiste Mouret and Stephane Doncieux
- I am Jürgen Schmidhuber, Ask Me Anything! by Jürgen Schmidhuber
- Deep Learning for Computer Vision by Justin Johnson
- The Full Reinforcement Learning Iceberg📝 by Joseph Suarez