• 9 min read
How to Fine-Tune Qwen2.5-VL with a Custom Dataset
Learn how to fine-tune Qwen2.5-VL for document processing using a custom dataset.
Blog
Aryan Vasudevan
Latest Posts by Aryan Vasudevan
• 9 min read
How to Use Roboflow CoreML Models and ESP32 Hardware for IoT
Learn how to use CoreML models trained on Roboflow to control hardware devices with an ESP32 device.
• 5 min read
How to Train YOLO11 Instance Segmentation on a Custom Dataset
Learn how to train a YOLO11 instance segmentation model with Roboflow.
• 4 min read
How to use YOLOE for Zero-Shot Object Detection & Segmentation
In computer vision, few model families have made as big an impact as YOLO. Originally designed for fast and accurate object detection, the YOLO architecture has evolved rapidly, now supporting both complex detection and segmentation tasks.
With the rise of YOLOE and other enhanced variants, it's now easier
• 3 min read
Reduce Jittery and Flickering Detections in Computer Vision
It's common in computer vision projects for bounding boxes to jump or flicker from frame to frame, especially when objects move quickly or lighting is challenging. This is because the model detections aren't perfect or consistent and, when visualized, the human eye sees lots of jittery
• 8 min read
How to Create a YOLOv11 Android App
Adding vision AI capabilities to your Android app is possible by deploying a custom YOLOv11 model on your device. Object detection models allow you to create lots of useful features like counting, measurement, reading text, and classification.
In this guide, you'll learn how to create a custom YOLOv11
• 9 min read
How to Build an iOS App with Visual AI Capabilities
In this guide, we’ll walk through using a custom object detection model tailored to identify glasses and show you how to seamlessly integrate it into an iOS app for instant live detection — all with minimal latency and maximum convenience.
0:00
/0:13
1×
Millions of people rely on
• 5 min read
Use Qwen2.5-VL for Zero-Shot Object Detection
Qwen2.5-VL is the latest addition to the Qwen vision-language model series, offering cutting-edge capabilities for image, text, and document understanding.
Available in three model sizes—3B, 7B, and 72B—it excels at tasks such as object detection, OCR for multi-language and rotated text, and structured data extraction from complex
• 7 min read
Use Gemini 2.5 for Zero-Shot Object Detection & Segmentation
Learn how to use Gemini 2.5 for zero-shot object detection and segmentation.
• 8 min read
Comparing Base and Fine-Tuned SmolVLM2 for OCR
In this guide, we will walk through how to fine-tune SmolVLM2 for OCR.
• 4 min read
Use Roboflow Workflows to Collect and Preprocess Image Training Data
Learn how to use Roboflow Workflows to collect and preprocess image training data for use in building a vision model.
• 9 min read
Creating a Cutting Safety Tool with Keypoint Detection
Learn how to create a tool that monitors for potentially hazardous posture when cutting food in the kitchen.
Stay Connected