Stars
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …
An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
[NeurIPS 2025] Official Implementation of DINO-Foresight: Looking into the Future with DINO
Code and Pretrained Models for ICLR 2023 Paper "Contrastive Audio-Visual Masked Autoencoder".
🎨 NeMo Data Designer: A general library for generating high-quality synthetic data from scratch or based on seed data.
Plotting heatmaps with the self-attention of the [CLS] tokens in the last layer.
[ICLR 2024] Official repository for "Vision-by-Language for Training-Free Compositional Image Retrieval"
Fara-7B: An Efficient Agentic Model for Computer Use
Official code release for "SuperBPE: Space Travel for Language Models"
Reference PyTorch implementation and models for DINOv3
DeepEP: an efficient expert-parallel communication library
General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]
MixtureVitae: A Permissive, High-Performance, Open-Access Pretraining Dataset
Kandinsky 5.0: A family of diffusion models for Video & Image generation
Manipulate audio with a simple and easy high level interface
Code for Machine Learning for Algorithmic Trading, 2nd edition.
Official Implementation of "MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation"
Fully automatic censorship removal for language models
The most open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.
Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.
Open-source framework for the research and development of foundation models.
An experimental implementation of compiler-driven automatic sharding of models across a given device mesh.