🎯
Highlights
- Pro
Lists (1)
Starred repositories
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).
The LRP Toolbox provides simple and accessible stand-alone implementations of LRP for artificial neural networks supporting Matlab and Python. The Toolbox realizes LRP functionality for the Caffe D…
Supplementary code for the paper "Hyperbolic Image Embeddings".
Dataset and starting code for visual entailment dataset
Code for the paper "Compositional Entailment Learning for Hyperbolic Vision-Language Models".
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
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