Welcome to the AI SandboxThe AI Sandbox is a weekly, hands-on learning space where faculty, researchers, and staff across campus can explore and experiment with real AI tools. Each session introduces models used in research, from image segmentation to text classification, and walks you through how to run them in your browser, step by step. No prior experience is required, just bring your laptop and curiosity!These are not lectures or office hours. You’ll follow guided demos, test out pre-trained models, and have time to explore either with example datasets or your own research material. Each week focuses on a different theme, with support provided throughout.Due to popular demand, registration is now required. Sessions are small to ensure everyone gets guided support, but you’re welcome to bring along colleagues; groups of up to five can attend together.Nest Session: Image Analysis with AIHow do AI models "see" an image? How do they detect, label, or even describe what’s inside a photo?This week’s Sandbox session introduces four powerful models that can do exactly that. You’ll learn how to upload images and use pre-trained models to identify objects, label regions, classify what’s in the frame, and even answer questions about what the image shows.Hands-on demos include:Segment Anything – Click and segment any object in an image, instantlyGrounding DINO – Detect objects using natural language prompts (e.g., "find the person")Vision Transformer (ViT) – Use deep learning to classify image contents (e.g., cat, tree, laptop)Qwen-VL (Qwen3) – Ask open-ended questions about an image and get intelligent responsesThis session is perfect for anyone working with visual data, whether you’re analyzing microscope slides, satellite images, or just curious about how image AI works.The Green Court building at 3520, Green Ct., MI 48105. The MIDAS offices are on the 3rd floor.The west side of the building is reserved for non-U-M use. There is a U-M yellow lot immediately to the east of the building. Do not park in the Black and Veatch parking lot.