Starred repositories
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
A curated list of foundation models for vision and language tasks
Library that provides metrics to assess representation quality
wolfecameron / nanoMoE
Forked from karpathy/nanoGPTAn extension of the nanoGPT repository for training small MOE models.
Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
Train a model to reason over your policies using deliberative alignment.
bknyaz / modded-nanogpt
Forked from KellerJordan/modded-nanogptNanoGPT (124M) in 3 minutes
Gemma open-weight LLM library, from Google DeepMind
Must-read papers on alignement, instrumental convergence, adversarial robustness and AI safety in general.
5
Updated Mar 5, 2025
This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"
This repository is a curated collection of resources, tutorials, and practical examples designed to guide you through the journey of mastering CUDA programming. Whether you're just starting or look…
Everything you need to build state-of-the-art foundation models, end-to-end.
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
A launch point for your personal nvim configuration
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
MineStudio: A Streamlined Package for Minecraft AI Agent Development
A generative world for general-purpose robotics & embodied AI learning.
Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [to appear at ICLR 2025]
Minimalistic, hackable PyTorch implementation of SimSiam in ~400 lines. Achieves good performance on ImageNet with ResNet50. Features distributed training, real-time KNN eval, and AMP. Perfect for …
Course to learn the basics of self supervised learning
TorchFix - a linter for PyTorch-using code with autofix support
Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wikitext-103 on a single A100 in <100 seconds. Scales to large…