We’re on a journey to advance and democratize artificial intelligence through open source and open science.

PhyCV: The First Physics-inspired Computer Vision Library - JalaliLabUCLA/phycv

Build 10x faster with the first fully native Graph-Vector Database combining the power of graph and vector types natively in Rust to build RAG and AI applications easily

HelixDB is a powerful, open-source, graph-vector database built in Rust for intelligent data storage for RAG and AI. - HelixDB/helix-db

We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perceptron (MLP) decoders. SegFormer has two appealing features: 1) SegForme…

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

We introduce Florence-2, a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-language tasks. While existing large vision models...

We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user...

The current state-of-the-art on COCO test-dev is Co-DETR. See a full comparison of 257 papers with code.

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2 - IDEA-Research/Grounded-SAM-2

Co-DETR (Detection Transformer) compiled from PyTorch to NVIDIA TensorRT - anenbergb/Co-DETR-TensorRT

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything - IDEA-Research/Grounded-S...

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2 - IDEA-Research/Grounded-SAM-2