Researchers at UCLA have developed an optical generative AI model that creates images using minimal energy and computational steps.
Key Details
- 1UCLA Samueli School of Engineering introduces a photonics-based generative AI system.
- 2The optical approach generates images in a single step, compared to hundreds or thousands for digital models.
- 3Experimental and numerical tests showed high-quality image generation on datasets including human faces and Van Gogh-inspired artwork.
- 4The system incorporates a physical key-lock mechanism for enhanced image security and privacy.
- 5Potential applications identified: biomedical imaging, diagnostics, augmented/virtual reality, and portable/wearable devices.
- 6The approach significantly lowers energy and water consumption compared to conventional generative AI.
Why It Matters
This breakthrough may enable sustainable, fast, and secure generative AI with applications in medical imaging, diagnostics, and beyond. Its reduced resource requirements are particularly relevant as the environmental impact of AI computing grows.
Source
EurekAlert
Related News
•EurekAlert
AI Framework Accelerates Aortic Aneurysm Risk Prediction from Imaging
Researchers developed BioPINN-LM, combining physics-informed neural networks and multimodal large language models to deliver fast, interpretable risk assessments for ascending thoracic aortic aneurysms.
•EurekAlert
Study Finds Patient Voices Missing in Generative AI Design for Oncology
A Flinders University-led review found patients and carers are rarely involved in shaping generative AI tools used in oncology.
•EurekAlert
Scripps Researchers Develop AI Foundation Model for ECG-Based Heart Disease Prediction
A new AI foundation model, ECG-CLIP, improves detection and prediction of multiple heart diseases using large-scale ECG and clinician note data.