The simplest, fastest repository for training/finetuning small-sized VLMs.

Lightweight coding agent that runs in your terminal

Tennis Detection and Visualization System An advanced computer vision system for tennis match analysis that tracks players and ball movement with high precision. The system uses YOLOv8 and custom-t…

Take your LLM to the optometrist.

Robust Speech Recognition via Large-Scale Weak Supervision

Run Segment Anything Model 2 on a live video stream

Visualize streams of multimodal data. Free, fast, easy to use, and simple to integrate. Built in Rust.

[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".

[CVPR 2025] UniK3D: Universal Camera Monocular 3D Estimation

A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms

This repository is an official implementation of the paper "LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection".

This project is designed to display how we can utilize deep learning methods for Sports Data Analytics.

​"Stamp-Signature-Segregate" is a tool for detecting and removing overlapping stamps and signatures in documents. It combines YOLO object detection, Nvidia's SegFormer for segmentation, and advance…

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

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

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

The home for open source maintainer chats

Solve Visual Understanding with Reinforced VLMs

YOLOv12: Attention-Centric Real-Time Object Detectors

Official implementation of the WACV 2025 ( Oral ) paper. RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision.

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

LLM training in simple, raw C/CUDA

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

🏀 Basketball Video Analysis: Leverage automated detection and tracking of players, ball, and team assignments using advanced object tracking, zero-shot classification, and keypoint detection with Y…

A tool for determining if a pickleball is in or out of bounds

tiny vision language model

Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥

A complete pipeline for fine-tuning YOLOv8 pose models with custom datasets. Supports automatic and semi-automatic annotation for efficient keypoint labeling.