Thinking in DAGs: How Humans and Agents Collaborate in Data Science
Chen Li As LLM agents increasingly participate in data science, a critical question emerges: what abstraction best supports humans…
Category: Publication
Demonstration of BobFlow: Human-Agent Collaboration Using Dataflows on Data Science Tasks
Bai, Jiadong; Huang, Yicong; Li, Chen VLDB (Demo track), 2026. Recent advances in large language models (LLMs) have made…
Click, Share, Learn: Teaching Data Science Using Apache Texera
Asad, Sarah; Liu, Xiaozhen; Park, Kun Woo; Lin, Xinyuan; Bai, Jiadong; Ni, Shengquan; Huang, Yicong; Li, Chen Click, Share,…
How Californians Tweet about Extreme Heat Events on Social Media: A Health Equity Perspective
Sriperumbudur, Gomathi B.; Fan, Yihang; Liu, Xiaozhen; Ma, Mingyu Derek; Wang, Wei; Li, Chen; Hopfer, Suellen How Californians Tweet…
Bundled for Success: A WfBench-Driven Assessment of Texera
Wang, Meng; Jahangiri, Shiva; Maheshwari, Ketan; Li, Chen Bundled for Success: A WfBench-Driven Assessment of Texera 1st Workshop on…
UDF-Centric Dataflow Systems for Supporting User-Defined Functions in Collaborative Data Science, AI, and ML
Huang, Yicong UDF-Centric Dataflow Systems for Supporting User-Defined Functions in Collaborative Data Science, AI, and ML (PhD Thesis) 2025.…
ML-Asset Management: Curation, Discovery, and Utilization
Wang, Mengying; Duan, Moming; Huang, Yicong; Li, Chen; He, Bingsheng; Wu, Yinghui ML-Asset Management: Curation, Discovery, and Utilization In:…
Responsive Retrieval of Consistent States in Pipelined Executions of Dataflows
Ni, Shengquan; Li, Chen Responsive Retrieval of Consistent States in Pipelined Executions of Dataflows 2025. Many modern analytics data…
Supporting Responsive Runtime Interactions and Multi-Tenant Cloud Services in Texera
Ni, Shengquan Supporting Responsive Runtime Interactions and Multi-Tenant Cloud Services in Texera (PhD Thesis) 2025. PDF
IcedTea: Efficient and Responsive Time-Travel Debugging in Dataflow Systems
Ni, Shengquan; Huang, Yicong; Wang, Zuozhi; Li, Chen IcedTea: Efficient and Responsive Time-Travel Debugging in Dataflow Systems In: Proc.…