Neha Sharma, leader of the notebooks and code authoring teams at Databricks, discusses their journey with the Databricks Assistant powered by large language models (LLMs), showcasing its ability to interpret queries, generate code, and debug errors. She explains how the integration of code, user data, network signals, and the development environment enables the assistant to provide context-aware responses. Neha outlines the three evaluation methods used: helpfulness benchmarks, side-by-side evaluations, and tracking user interactions. She highlights ongoing improvements through model tuning and prompt adjustments and discusses future plans to fine-tune models with Databricks-specific knowledge for personalized user experiences.

Nyla Worker, a leader in AI character designer at Convai, sheds light on innovative strategies in NPC behavior simulation and management. Building on her experience at Nvidia, Nyla outlines the comprehensive process of creating lifelike, interactive AI characters for varied applications ranging from gaming to brand representation. She elaborates on the nuanced construction of these digital personas, involving character mind crafting with personality traits, backstory, and narrative design integrated into large-scale interactive environments like Unreal and Unity engines.

Explore the recent advances in multimodal LLMs, or Large Multimodal Models, along with what it means for the RAG applications, and what the gaps are still in our ability to process multimodal data.

Kelsey demystifies extracting and applying fashion colors from product images to enhance e-commerce search algorithms.

Reading text might be easy with LLMs, however when you are reading PDFs with charts and tables - you only process the text and not the charts. In this talk, Hamza explores various techniques using multimodal models to ingest important charts and tables and explore how you can make them part of the RAG architecture.

Beginning with an overview of spatialedge.ai, the company spearheading this innovative approach, the talk navigated through the vast landscape of the platform's extensive data backend. Spanning over two decades of historical data alongside real-time data streams, this backend serves as the bedrock for informed decision-making. Central to the discussion was the fully automated trading strategies which are developed and trained to capitalise on market dynamics, as well as the rigorous performance benchmarks these strategies must meet before being included into the fund's portfolio. Transitioning to the operational architecture, the talk provided a glimpse into the intricacies of strategy/model deployments, hosting, monitoring, and the CICDCT pipeline. These facets collectively ensure the seamless execution and optimisation of trading strategies, underscoring the sophistication of the algorithmic hedgefund's operational framework.

An introduction to using Synthetic Data for Computer Vision tasks.

Deploying a time series model in Vertex AI may initially appear straightforward, but unique attributes in the use case can present challenges. Catch Adam Hjerpe's session to gain insights into the challenges faced during deployment, how they were overcome, and the valuable lessons learned throughout the process. Ensure you are well informed about the limitations before embarking on your own deployment journey.