Towards Efficient Semantic Query Processing Engines

Abstract: Large language models (LLMs) have expanded the scope of databases from purely relational to semantic query processing engines. These engines support SQL queries with AI operators on multimodal data, configured via natural language instructions, that process functions requiring deep semantic understanding of data.  Semantic query processing has been adopted quickly in industry. However, the high overheads of LLM invocations limit its scalability.

In my talk, I will focus on methods that make semantic query processing more efficient. First, I will present SemBench, the "TPC-H of semantic query processing", enabling us to benchmark cost-quality tradeoffs realized by semantic query processing engines. Second, I will discuss our work on ThalamusDB, leveraging ideas from approximate query processing and specialized semantic operator implementations to speed up semantic queries. I will conclude by describing ongoing projects and avenues for future research.

Bio: Immanuel Trummer is an associate professor of computer science at Cornell University. His research focuses on making data analysis more efficient and more user-friendly, often leveraging techniques from the area of machine learning, in particular, large language models. His papers were selected for "Best of VLDB", "Best of SIGMOD", and the CACM Research Highlight Award. He received an NSF CAREER grant for his work on database tuning via LLMs and multiple Google Faculty Research Awards. He is also the author of the book "Data Analysis with LLMs", now available in five languages. 

Embrace the gap: Learnings from Production AI Systems

Abstract: Large language models and AI agents are advancing rapidly, yet a persistent gap remains between model capabilities and the systems needed to deliver reliable, user-facing products. In production, the model is not the product: predictions must be translated into decisions under evolving workloads, incomplete context, bounded authority, and noisy, delayed feedback. This talk draws on experience building and operating AI-driven systems at scale—including AI driven resource scaling (Amazon Redshift RAIS), query execution time prediction (Stage), LLM-based database performance debugging (Panda), and adaptive NL-to-SQL pipelines (TailorSQL, SQLens)—to surface learnings. We argue that the messiness of production AI—bridging changing models, evolving user expectations, and stable product contracts through lifelong learning loops—is fertile ground for systems research, and we outline open challenges in organizing agent state, runtime monitoring, and adaptive reconfiguration of compound AI pipelines.

Bio: Balakrishnan (Murali) Narayanaswamy is a Principal Machine Learning Scientist at Amazon Web Services, where he leads a team in AWS AI. His research lies at the intersection of AI, ML, systems, optimization, learning, and inference. He has led the science teams behind Amazon Redshift ML, DevOps Guru for RDS, and GuardDuty RDS Protection, and, more recently, AI-driven scaling and optimization in Redshift Serverless, Amazon Q Generative SQL, Structured Knowledge Bases in Amazon Bedrock and built agents Amazon Quick. His work on Amazon Personalize received the Best Paper Award in the Applied Data Science Track at KDD 2020, and their recent research on ML for systems appears at venues including Neurips, ICML, AAAI, UAI, SIGMOD 2023 and 2024 and VLDB and CIDR 2025.