Part of Techlahoma Foundation - 19 groups
159 members
Connect with other software engineers in Oklahoma interested in AI and software development. Our in-person meetups offer interactive workshops, hands-on demos, and engaging discussions. Open to engineers at all experience levels.
1
We will first cover the basics of diffusion, the process by which we gradually add noise to structured data until pure noise is achieved, and how to reverse it back to a clean image with the help of deep learning models. Diffusion is most prominent with image generation, where we start from a noisy image and leverage our model to generate a clean image of our choosing. But can we take it further, by applying this same diffusion philosophy to generate a full, coherent LLM response simultaneously? We dive into how this can be achieved, covering both theoretical and implementation details, the advantages diffusion-LLMs have over traditional LLMs, and their limitations.
7
