Chenglong Wang

I'm a researcher in Microsoft Research. How can human and AI agents work together to solve challenging data analysis tasks? We are developing interactive AI systems based on our studies of human behavior and AI capabilities towards this goal.

I got my PhD in University of Washington. I was lucky to work with Ras Bodik and Alvin Cheung, and we built program synthesis-powered tools for data analysis.

I studied in Peking University. I was lucky to work with Zhenjiang Hu and Yingfei Xiong on program transformation.

Publications

Conference

• DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing (CHI 2024, Best Paper Award)

  Priyan Vaithilingam, Elena L. Glassman, Jeevana Priya Inala, Chenglong Wang

  [paper]
• How Do Analysts Understand and Verify AI-Assisted Data Analyses? (CHI 2024)

  Ken Gu , Ruoxi Shang, Tim Althoff, Chenglong Wang, and Steven M. Drucker

  [paper]
• PhotoScout: Synthesis-Powered Multi-Modal Image Search (CHI 2024)

  Celeste Barnaby, Jocelyn Chen, Chenglong Wang, Isil Dillig

  [paper]
• Is Self-Repair a Silver Bullet for Code Generation? (ICLR 2024)

  Theo X. Olausson, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao, Armando Solar-Lezama

  [paper]
• Data Formulator: AI-powered Concept-driven Visualization Authoring (VIS 2023, Honorable Mention)

  Chenglong Wang, John Thompson, Bongshin Lee

  [paper] [overview-video] [blog]
• Fast and Reliable Program Synthesis via User Interaction (ASE 2023)

  Yanju Chen, Chenglong Wang, Xinyu Wang, Osbert Bastani, Yu Feng
• On the Design of AI-powered Code Assistants for Notebooks (CHI 2023)

  Andrew McNutt, Chenglong Wang, Rob DeLine, Steven M. Drucker

  [paper]
• Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions (ICLR 2023)

  Ansong Ni, Jeevana Priya Inala, Chenglong Wang, Oleksandr Polozov, Christopher Meek, Dragomir Radev, Jianfeng Gao

  [paper]
• Fault-Aware Neural Code Rankers (NeurIPS 2022)

  Jeevana Priya Inala, Chenglong Wang, Mei Yang, Andres Codas, Mark Encarnación, Shuvendu Lahiri, Madan Musuvathi, Jianfeng Gao

  [paper]
• Type-Directed Synthesis of Visualizations from Natural Language Queries (OOPSLA 2022)

  Jocelyn Chen, Shankara Pailoor, Celeste Barnaby, Abby Criswell, Chenglong Wang, Greg Durrett, Isil Dillig

  [paper]
• Synthesizing Analytical SQL Queries from Computation Demonstration (PLDI 2022, Distinguished Paper)

  Xiangyu Zhou, Rastislav Bodik, Alvin Cheung, Chenglong Wang

  [paper] [slides:pdf]
• Falx: Synthesis-powered Visualization Authoring (CHI 2021, Best Paper Award)

  Chenglong Wang, Yu Feng, Rastislav Bodik, Isil Dillig, Alvin Cheung, Amy J. Ko

  [paper] [preview video] [CHI talk video] [blog post]
• Program Synthesis using Deduction-Guided Reinforcement Learning (CAV 2020)

  Yanju Chen, Chenglong Wang, Osbert Bastani, Isil Dillig, Yu Feng

  [paper]
• Scout: Rapid Exploration of Interface Layout Alternatives through High-Level Design Constraints (CHI 2020)

  Amanda Swearngin, Chenglong Wang, Alannah Oleson, James Fogarty, Amy J. Ko.

  [paper]
• Visualization by Example (POPL 2020)

  Chenglong Wang, Yu Feng, Ras Bodik, Alvin Cheung, Isil Dillig.

  [paper] [slides:pdf]
• Learning Transferable Graph Exploration (NeurIPS 2019)

  Hanjun Dai, Yujia Li, Chenglong Wang, Rishabh Singh, Po-Sen Huang, Pushmeet Kohli.

  [paper]
• Knowing When to Stop: Evaluation and Verification of Conformity to Output-size Specs (CVPR 2019)

  Chenglong Wang, Rudy Bunel, Krishnamurthy Dvijotham, Po-Sen Huang, Edward Grefenstette, Pushmeet Kohli.

  [paper] [poster:pdf]
• Speeding up Symbolic Reasoning for Relational Queries (OOPSLA 2018)

  Chenglong Wang, Alvin Cheung, Ras Bodik.

  [paper] [slides:pdf] [project-site]
• Formalizing Visualization Design Knowledge as Constraints: Actionable and Extensible Models in Draco (InfoVis 2018, Best Paper)

  Dominik Moritz, Chenglong Wang, Greg L. Nelson, Halden Lin, Adam M. Smith, Bill Howe, Jeffrey Heer.

  [paper] [project-site]
• Natural Language to Structured Query Generation via Meta-Learning (NAACL 2018) (short paper)

  Po-Sen Huang, Chenglong Wang, Rishabh Singh, Wen-tau Yih, Xiaodong He.

  [paper] [source]
• NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System. (LREC 2018)

  Xi Victoria Lin, Chenglong Wang, Luke Zettlemoyer, Michael D. Ernst.

  [paper] [source]
• Synthesizing Highly Expressive SQL Queries from Input-Output Examples (PLDI 2017)

  Chenglong Wang, Alvin Cheung, Rastislav Bodik.

  [paper] [slides:pdf] [project-site]
• Cosette: An Automated SQL Solver (CIDR 2017)

  Shumo Chu, Chenglong Wang, Konstantin Weitz, Alvin Cheung.

  [paper] [project-site]
• Transforming Programs between APIs with Many-to-Many Mappings (ECOOP 2016)

  Chenglong Wang, Jiajun Jiang, Jun Li, Yingfei Xiong, Xiangyu Luo, Lu Zhang, Zhenjiang Hu.

  [paper] [slides:pdf]

Random

• Testing query execution engines with mutations (DBTest 2020)

  Xinyue Chen, Chenglong Wang, Alvin Cheung.
• Execution-Guided Neural Program Decoding (NAMPI 2018)

  Chenglong Wang, Po-Sen Huang, Alex Polozov, Marc Brockschmidt, Rishabh Singh.

  [paper]
• Demonstration of the Cosette Automated SQL Prover (SIGMOD Demo 2017, Best Demo)

  Shumo Chu, Daniel Li, Chenglong Wang, Alvin Cheung, Dan Suciu.

  [demo] [paper]
• Interactive Query Synthesis from Input-Output Examples (SIGMOD Demo 2017)

  Chenglong Wang, Alvin Cheung, Rastislav Bodik.

  [demo] [paper]
• Composable and Hygienic Typed Syntax Macros (SAC 2015)

  Cyrus Omar, Chenglong Wang, Jonathan Aldrich.

  [paper] [slides:pdf]
• SWIN: Towards Type-Safe Java Program Adaptation between APIs (PEPM 2015)

  Jun Li, Chenglong Wang, Yingfei Xiong, Zhenjiang Hu.

  [paper] [tech-report]

Fun

I enjoy playing piano, climbing and skydiving.