talk-data.com

Open-source is helping AI become more aligned, trustworthy, accessible and creating opportunities at a scale we’ve never experienced before. The future of AI is open and bountiful… will you be a part of it?

Synopsis: Embark on an enlightening journey with Noble as he tackles the challenges of integrating Large Language Models (LLMs) into enterprise environments. Understand the inherent unreliability of these models and explore innovative solutions, ranging from vector databases to prompt chaining, that aim to enhance the trustworthiness of LLMs in crucial applications.

Delve into the fascinating realm of visualization generation with LIDA, a tool that seamlessly integrates LLMs and Image Generation Models (IGMs). Victor will explore the challenges, designs, and innovations in the world of LLM-enabled visualization tools.

Navigating the development of an assistive indoor technology for the visually impaired, my PhD journey intersected with Google's advanced tools. Tasked with optimizing location accuracy on budget smartphones, I integrated methodologies reminiscent of those in autonomous vehicle systems. The application utilized TensorFlow Lite's version of YOLO from GCP for obstacle detection, enhanced with transfer learning to widen object recognition capabilities. Google's text-to-speech and speech recognition APIs became pivotal, filling the gap in my resource constraints. This talk underscores the power of leveraging accessible tools in creating impactful, innovative tech solutions, while offering insights into the practical challenges and successes of my endeavor.

Explore how Large Language Models (LLMs) are bridging the gap between human thought processes and discrete digital operations. Allen will provide insights on using LLMs for tasks such as SQL queries, creating search embeddings, and generating human-friendly responses.