Chunwei Liu

Prune First, Decide Fast: Scalable Semantic Query Processing with JEVDB

Semantic database systems extend SQL with foundation-model inference over unstructured data, but current engines rely heavily on autoregressive LLMs for discrete relational decisions, creating high latency and monetary cost. We present JEVDB, a scalable semantic database system that uses fast, typed decision models for...

Fail Loudly: An Auditable Runtime for Agentic Data Analysis

Large language models (LLMs) have enabled data-science agents to automate multi-step analyses over heterogeneous files. However, incorrect choices regarding data sources, scope, or statistical definitions often lead to silent errors: computations execute successfully but produce plausible yet incorrect outputs that fai...

iPDB: SQL with ML and LLM Predicates (Towards a Database Engine for AI)

iPDB is demonstrated, a system that supports in-database LLM inference using an extended declarative SQL syntax and new optimizations that result in efficient query processing of LLM-enabled SQL queries that outperform state-of-the-art systems.

TransForm: Dynamic Format Selection for MCP Tool Outputs in Agentic Data Systems

TabClean: Scalable Tabular Data Cleaning via Reusable LLM-Synthesized Programs

TabClean is presented, a cost-efficient and training-free tabular data cleaning system in which LLM agents synthesize reusable code for error detection and correction, making LLM usage a largely one-time rather than recurring cost.