This demonstration showcases a real-time vision-language inference pipeline running on an AMD Radeon™ integrated GPU, highlighting multimodal AI capabilities on power-efficient embedded platforms. The system processes live or recorded video streams and enables interactive question answering based on visual scene understanding. A lightweight Vision-Language Model (VLM) is deployed to jointly interpret visual inputs and natural language queries, enabling use cases such as object identification, scene description, and contextual reasoning. The pipeline supports interactive, frame-level querying, allowing users to ask questions about the current video frame and receive model-generated responses in real time.
