Non-LLM neural networks & ML foundations for expert learners
100 resources · page 2 of 4
NeuralPDE.jl
by SciML Open Source Scientific Machine Learning
SciML NeuralPDE.jl GitHub repo: physics-informed neural network solvers for PDEs in Julia.
OpenAI Spinning Up
by OpenAI
OpenAI Spinning Up: educational guide to deep reinforcement learning with algorithm explanations and code.
OpenRLHF
by OpenRLHF
OpenRLHF GitHub repo: Ray and vLLM based framework for RLHF and agentic RL training.
OpenSpiel
DeepMind OpenSpiel GitHub repo: environments and algorithms for reinforcement learning and search in games.
PyTorch Geometric
PyTorch Geometric (PyG) documentation: library for building and training graph neural networks.
Qwen3-VL
by Qwen
QwenLM Qwen3-VL GitHub repo: multimodal large language model series with usage code.
RecBole
by RUCAIBox
RUCAIBox RecBole GitHub repo: unified library of recommendation algorithms for reproducible comparison.
Recommenders
Recommenders GitHub repo: examples and utilities for building recommendation systems.
SciML Book (MIT 18.337)
by Chris Rackauckas (MIT 18.337)
SciML Book: lecture notes from MIT 18.337 on parallel computing and scientific machine learning.
slime
by THUKEG
THUDM slime GitHub repo: Megatron and SGLang based framework for RL post-training at scale, used for GLM.
Solver-in-the-Loop
by TUM Physics-based Simulation
TUM Solver-in-the-Loop GitHub repo: learning from differentiable physics to correct iterative PDE solvers.
TabPFN (Prior Labs, Freiburg)
by Prior Labs
Prior Labs TabPFN GitHub repo: foundation model for tabular classification and regression.
THUDM (Tsinghua KEG) GitHub
by THUKEG
THUDM GitHub organisation (Tsinghua KEG and Zhipu): code for ChatGLM, GLM-4, CogVLM, CogVideoX and AgentBench.
google-research/timesfm
Google Research TimesFM GitHub repo: pretrained time-series foundation model for forecasting.
pytorch-image-models (timm)
by Hugging Face
Hugging Face timm GitHub repo: PyTorch image models, encoders and training scripts.
Ultralytics YOLO
by Ultralytics
Ultralytics GitHub repo: YOLO models for object detection, segmentation and pose estimation.
verl
by verl-project
verl GitHub repo (originally ByteDance): RL post-training framework used for RLVR.
verl / HybridFlow
by verl-project
verl GitHub repo: HybridFlow framework for distributed RL post-training of LLMs.
VinAI
by VinAI
VinAI site: Vietnamese company doing AI research and building applied AI products.
WGA: AI provisions of the 2023 MBA
by Writers Guild of America West
WGA page on artificial intelligence provisions in the 2023 Minimum Basic Agreement.
X recommendation algorithm
twitter the-algorithm GitHub repo: source code of the X recommendation algorithm services.
XGBoost Documentation
XGBoost documentation: distributed gradient boosting library, a standard non-neural baseline for tabular data.
Agent57
by Adrià Puigdomènech Badia et al. (Google)
arXiv paper (2020) introducing Agent57, the first agent to exceed the human baseline on all 57 Atari games.
ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)
by Alex Krizhevsky, Ilya Sutskever and Geoffrey E. Hinton (University of Toronto)
NeurIPS paper (PDF, 2012) AlexNet: ImageNet classification with deep convolutional neural networks.
Faster sorting algorithms discovered using deep reinforcement learning (AlphaDev)
by Daniel J. Mankowitz et al. (Google DeepMind)
Nature paper (2023) on AlphaDev discovering faster sorting algorithms with deep RL.
Mastering the game of Go with deep neural networks and tree search (AlphaGo)
by David Silver et al. (DeepMind)
Nature paper (2016) on AlphaGo, mastering Go with deep neural networks and tree search.
Grandmaster level in StarCraft II using multi-agent reinforcement learning (AlphaStar)
by Oriol Vinyals et al. (DeepMind)
Nature paper (2019) on AlphaStar reaching grandmaster level in StarCraft II with multi-agent RL.
Discovering faster matrix multiplication algorithms with reinforcement learning (AlphaTensor)
by Alhussein Fawzi et al. (Google DeepMind)
Nature paper (2022) on AlphaTensor discovering faster matrix multiplication algorithms with RL.
AlphaZero
by David Silver et al. (DeepMind)
arXiv paper (2017) introducing AlphaZero, mastering chess and shogi through self-play reinforcement learning.
Chronos: Learning the Language of Time Series
by Abdul Fatir Ansari et al. (Amazon)
arXiv paper (2024) introducing Chronos, pretrained time-series forecasting models using language-model tokenization.
DenseNet
by Gao Huang et al. (Cornell University)
arXiv paper (2016) "Densely Connected Convolutional Networks", introducing DenseNet, where each layer receives feature maps from all earlier layers.
DETR
by Nicolas Carion et al. (Meta)
arXiv HTML version of the DETR paper (2020) on end-to-end object detection with transformers.