Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Learn AI and LLMs from scratch using free resources

Standard Open Arm 100

"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspi…

Building a GPT like model in Python from scratch.

[ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

The official gpt4free repository | various collection of powerful language models | o4, o3 and deepseek r1, gpt-4.1, gemini 2.5

Voyager is an interactive RGBD video generation model conditioned on camera input, and supports real-time 3D reconstruction.

DeepSeek

Introduction to Machine Learning Systems

⏩ Ship faster with Continuous AI. Open-source CLI that can be used in TUI mode as a coding agent or Headless mode to run background agents

Context engineering is the new vibe coding - it's the way to actually make AI coding assistants work. Claude Code is the best for this so that's what this repo is centered around, but you can apply…

Deep learning model for classification of dog and cat images

Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

Train best LLM possible on 1 x NVIDIA T4 (Google Colab, Kaggle,...) GPU

OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention

H-Net: Hierarchical Network with Dynamic Chunking

NEO Series: Native Vision-Language Models from First Principles

Contexts Optical Compression

Java solution for most popular Leetcode questions

Text, image, audio, video unified into a single diffusion model with 1 latent space.

Transform research papers and mathematical concepts into stunning visual explanations (using the manim engine), powered by AI

[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Supporting code for the blog post on modular manifolds.

AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.

verl: Volcano Engine Reinforcement Learning for LLMs

Automatic Video Generation from Scientific Papers

The official implementation of "ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning"