6 papers
A Decade of Systems for Human Data Interaction
Eugene Wu, Yiru Chen, Haneen Mohammed +1
Human-data interaction (HDI) presents fundamentally different challenges from traditional data management. HDI systems must meet latency, correctness, and consistency needs that st…
Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets
Gagan Bansal, Wenyue Hua, Zezhou Huang +21
As LLM agents advance, they are increasingly mediating economic decisions, ranging from product discovery to transactions, on behalf of users. Such applications promise benefits bu…
GPU Acceleration of SQL Analytics on Compressed Data
Zezhou Huang, Krystian Sakowski, Hans Lehnert +5
GPUs are uniquely suited to accelerate (SQL) analytics workloads thanks to their massive compute parallelism and High Bandwidth Memory (HBM) -- when datasets fit in the GPU HBM, pe…
Data Cleaning Using Large Language Models
Shuo Zhang, Zezhou Huang, Eugene Wu
Data cleaning is a crucial yet challenging task in data analysis, often requiring significant manual effort. To automate data cleaning, previous systems have relied on statistical…
Disambiguate Entity Matching using Large Language Models through Relation Discovery
Zezhou Huang
Entity matching is a critical challenge in data integration and cleaning, central to tasks like fuzzy joins and deduplication. Traditional approaches have focused on overcoming fuz…
Cocoon: Semantic Table Profiling Using Large Language Models
Zezhou Huang, Eugene Wu
Data profilers play a crucial role in the preprocessing phase of data analysis by identifying quality issues such as missing, extreme, or erroneous values. Traditionally, profilers…