Reading

Oct 08, 2025

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density

Oct 08, 2025

How to build a consistency model: Learning flow maps via self-distillation

Oct 07, 2025

Less is More: Recursive Reasoning with Tiny Networks

Oct 07, 2025

Steering Your Diffusion Policy with Latent Space Reinforcement Learning

Oct 06, 2025

Fast Transformer Decoding: One Write-Head is All You Need

Oct 06, 2025

PyTorch internals

Oct 06, 2025

ALIGNMENT

Oct 03, 2025

An Opinionated Guide to ML Research

Oct 02, 2025

Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models

Oct 01, 2025

Tinker

Sep 29, 2025

Preemptive Detection and Steering of LLM Misalignment via Latent Reachability

Sep 29, 2025

Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model

Sep 29, 2025

Diffusion Policy: Visuomotor Policy Learning via Action Diffusion

Sep 29, 2025

Equivariant Diffusion Policy

Sep 28, 2025

Failing to Understand the Exponential, Again

Sep 21, 2025

Variational Shape Inference for Grasp Diffusion on SE(3)

Sep 15, 2025

Defeating Nondeterminism in LLM Inference

Mar 30, 2025

Tracing the thoughts of a large language model

Mar 30, 2025

On the Biology of a Large Language Model

Mar 17, 2025

Introduction to Quantum Information Science Lecture Notes

Mar 09, 2025

sesame

Mar 09, 2025

Understanding Transformers... (beyond the Math)

Feb 23, 2025

The Ultra-Scale Playbook: Training LLMs on GPU Clusters

Feb 18, 2025

Useless Use of Cat Award

Feb 16, 2025

"A calculator app? Anyone could make that."

Feb 10, 2025

Training language models to follow instructions with human feedback

Feb 09, 2025

Three Observations

Feb 07, 2025

A Little Bit of Reinforcement Learning from Human Feedback

Feb 07, 2025

sacred.computer

Jan 29, 2025

Quotes

Jan 29, 2025

How has DeepSeek improved the Transformer architecture?

Jan 28, 2025

Essential template metaprogramming

Jan 27, 2025

Evolving Deeper LLM Thinking

Jan 25, 2025

How I became a machine learning practitioner

Jan 23, 2025

PythonRobotics

Jan 22, 2025

Announcing The Stargate Project

Jan 21, 2025

Interfaces

Jan 21, 2025

Predicting Human Brain States with Transformer

Jan 20, 2025

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Jan 14, 2025

a reinforcement learning guide

Jan 13, 2025

Agents

Jan 11, 2025

200Bn Weights of Responsibility

Jan 11, 2025

Godly

Jan 11, 2025

Vim Kōans

Jan 10, 2025

Static search trees: 40x faster than binary search

Jan 08, 2025

omi: thought to action

Jan 07, 2025

Fauna Robotics

Jan 07, 2025

Perhaps Not The Answer You Were Expecting But You Asked For It

Dec 28, 2024

The 2025 AI Engineering Reading List

Dec 19, 2024

GPU Glossary

Dec 19, 2024

MoonBit Compiler

Dec 17, 2024

Robotic Manipulation

Dec 17, 2024

Underactuated Robotics

Dec 14, 2024

Teaching GHC how to play Minesweeper

Dec 06, 2024

Introducing OpenAI o1

Dec 04, 2024

John Galt (Pseudonymous Designer)

Dec 02, 2024

Simple but Powerful Pratt Parsing

Dec 02, 2024

On the Glucose SAT solver

Dec 01, 2024

Glucose SAT Solver

Dec 01, 2024

Thirty Observations at Thirty

Nov 29, 2024

The UX of LEGO Interface Panels

Nov 29, 2024

Rowan Zellers (Research @ OpenAI)

Nov 28, 2024

Dear future undergraduate researcher

Nov 28, 2024

Competitive Programmer's Handbook

Nov 23, 2024

Untangling Lifetimes: The Arena Allocator

Nov 23, 2024

Rachit Nigam (EECS Professor @ MIT)

Nov 19, 2024

Guillermo Angeris (Chief Scientist @ Bain Capital Crypto)

Nov 19, 2024

Floating Point Instructions

Nov 19, 2024

Lujun's Resources

Nov 18, 2024

SciML

Nov 16, 2024

OpenAI Email Archives (from Musk v. Altman)

Nov 16, 2024

Implementing the Simple C Compiler

Nov 14, 2024

Expository papers

Nov 13, 2024

Personality Basins

Nov 12, 2024

reflections on palantir

Nov 12, 2024

Jason Liu (Instructor Guy)

Nov 12, 2024

Jack Morris (Cornell Tech, FAIR, Google Brain)

Nov 12, 2024

Deep Learning, NLP, and Representations

Nov 05, 2024

Setting Your Pet Rock Free.

Aug 14, 2024

Algorithms for Decision Making

Aug 12, 2024

Evaluating ∇f(x) is as fast as f(x)

Aug 12, 2024

Reinforcement Learning from Human Feedback Book

Aug 12, 2024

Mathematical Foundations of Reinforcement Learning

Aug 11, 2024

Animated AI

Aug 07, 2024

Learning to Move with Affordance Maps

Aug 07, 2024

Imitation Learning

Aug 06, 2024

Algorithms for Modern Hardware

Aug 05, 2024

bytecode interpreters for tiny computers

Aug 03, 2024

Latency Numbers Every Engineer Should Know

Jul 28, 2024

The Matrix Calculus You Need For Deep Learning

Jul 28, 2024

A Recipe for Training Neural Networks

Jul 28, 2024

Practical Deep Learning

Jul 25, 2024

A (Long) Peer into Reinforcement Learning

Jul 23, 2024

Open Source AI Is the Path Forward

Jul 23, 2024

The Llama 3 Herd of Models

Jul 21, 2024

Mamba: The Hard Way

Jul 18, 2024

CleanRL (Clean Implementation of RL Algorithms)

Jul 18, 2024

Policy Gradient Demystified

Jul 17, 2024

Prover-Verifier Games improve legibility of language model outputs

Jul 16, 2024

Codestral Mamba

Jul 14, 2024

An extended collection of matrix derivative results for forward and reverse mode algorithmic differentiation

Jul 12, 2024

Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers

Jul 12, 2024

Modularized Implementation of Deep RL Algorithms in PyTorch

Jul 10, 2024

ML Code Challenges

Jul 10, 2024

lucidrains

Jul 05, 2024

From Autoencoder to Beta-VAE

Jul 05, 2024

Tutorial on Variational Autoencoders

Jul 01, 2024

The Super Effectiveness of Pokémon Embeddings Using Only Raw JSON and Images

Jul 01, 2024

Popular Model-free Reinforcement Learning Algorithms

Jun 29, 2024

Auto-Encoding Variational Bayes

Jun 29, 2024

Stanford CS234: Reinforcement Learning Spring 2024

Jun 29, 2024

Policy Gradient Algorithms

Jun 28, 2024

How to Optimize a CUDA Matmul Kernel for cuBLAS-like Performance: a Worklog

Jun 27, 2024

Meta Large Language Model Compiler: Foundation Models of Compiler Optimization

Jun 27, 2024

KAN: Kolmogorov-Arnold Networks

Jun 26, 2024

Higher-order Virtual Machine 2

Jun 26, 2024

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities

Jun 25, 2024

The Wi-Fi only works when it's raining

Jun 25, 2024

Yacine (Software @ X)

Jun 25, 2024

Andrej Karpathy (OpenAI, Tesla)

Jun 25, 2024

Lilian Weng (Safety @ OpenAI)

Jun 25, 2024

Einops: Clear and Reliable Tensor Manipulations with Einstein-like Notation

Jun 25, 2024

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Jun 25, 2024

Formal Algorithms for Transformers

Jun 25, 2024

A high-bias, low-variance introduction to Machine Learning for physicists

Jun 25, 2024

Attention is All You Need

Jun 25, 2024

Generative Adversarial Nets

Jun 25, 2024

Gradient-Based Learning Applied to Document Recognition

Jun 25, 2024

Diffusion Models

Jun 25, 2024

UGeneva 14x050 Deep Learning Course

Jun 25, 2024

The Transformer Family Version 2.0

Jun 25, 2024

Algebra, Topology, Differential Calculus, and Optimization Theory For Computer Science and Machine Learning

Jun 25, 2024

UToronto CSC321 Lecture 10: Automatic Differentiation

Jun 25, 2024

ML Interviews Book

Jun 25, 2024

Papers With Code

Jun 25, 2024

AI by Hand

Jun 25, 2024

The Matrix Calculus You Need For Deep Learning

Jun 25, 2024

Karpathy's MinBPE

Jun 25, 2024

index.globe.engineer

Jun 25, 2024

Autodidax

Jun 25, 2024

Ilya's 30u30

Jun 25, 2024

rsrch.space

Jun 25, 2024

Ishan's Idea List

Jun 25, 2024

The Annotated Transformer

Jun 25, 2024

The Little Book of Deep Learning

Jun 25, 2024

Transformers from Scratch