Invited Talk, MITxISC AI Speaker Series, Cambridge, MA
Invited talk on bridging semantic operator systems and Deep Research to build a general-purpose runtime for AI-driven analytics. Covered the evolution from Palimpzest’s declarative programming model and Abacus’ cost-based optimizer to our vision for an AI query engine for Deep Research.
Invited Talk, UPenn DB Seminar, Philadelphia, PA
Invited talk on Palimpzest and Abacus, our cost-based optimizer for semantic operator systems, presented at the University of Pennsylvania Database Seminar.
Invited Talk, Google DataML Talk Series, Mountain View, CA
Invited talk on cost-based optimization for semantic operators and Deep Research, presented as part of the DataML talk series at Google.
Conference Talk, CIDR 2026,
Presented our vision paper on combining the optimized execution of semantic operators with the flexibility and dynamic query planning of Deep Research systems to create a runtime for AI-driven analytics.
Conference Talk, CIDR 2025,
Presented our vision paper on Palimpzest, a system that enables anyone to process AI-powered analytical queries simply by defining them in a declarative language. The system uses its cost optimization framework to implement the query plan with the best trade-offs between runtime, financial cost, and output data quality.
Conference Talk, VLDB 2023, Vancouver, BC, Canada
Presented our work on InQuest, a system for accelerating aggregation queries on unstructured streams of data with statistical guarantees on query accuracy. InQuest leverages inexpensive approximation models (“proxies”) and sampling techniques to limit the execution of an expensive high-precision model (an “oracle”) to a subset of the stream.