Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.

Trying to make it easier to use JEPAs :)

A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

Continuous Thought Machines, because thought takes time and reasoning is a process.

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[DEIMv2] Real Time Object Detection Meets DINOv3

Notebooks for RAG improving workshop, using HackerNews data

[MICCAI 2025] Revisiting 3D Medical Scribble Supervision: Benchmarking Beyond Cardiac Segmentation

An image retrieval model for any localization task

Integrating histology and spatial transcriptomics - NeurIPS 2024

Official code release for Delta Activations: A Representation for Finetuned Large Language Models

This is the Rust course used by the Android team at Google. It provides you the material to quickly teach Rust.

[ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking

Make your calibration dreams come true. ros2_calib is a Multi-Sensor Calibration Tool using ROS2 mcap recordings with direct URDF export.

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

Henry: Hugo theme meant for a gorgeous reading experience and packed with features

Open source image background removal model

Blueprint for Ingesting massive volumes of live or archived videos and extract insights for summarization and interactive Q&A

🔥 Clone and recreate any website as a modern React app in seconds

Import your LeRobot format dataset into FiftyOne format

Complete solutions to the Programming Massively Parallel Processors Edition 4

Train transformer language models with reinforcement learning.