A Pragmatic VLA Foundation Model

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents

This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

[CVPR 2025] MINIMA: Modality Invariant Image Matching

Speed up model training by fixing data loading.

State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

Collection of AWESOME vision-language models for vision tasks

A Datacenter Scale Distributed Inference Serving Framework

Code from the paper "Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models"

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

Zero-shot Object Counting with Good Exemplars[ECCV 2024]

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual Language Models

Cost-efficient and pluggable Infrastructure components for GenAI inference

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

Janus-Series: Unified Multimodal Understanding and Generation Models

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

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

[CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

Python tool for converting files and office documents to Markdown.

LLM101n: Let's build a Storyteller

This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Accessible large language models via k-bit quantization for PyTorch.

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities