Benjie Wang

Benjie Wang

Postdoctoral Scholar

University of California, Los Angeles

I am a Postdoctoral Scholar in the Statistical and Relational Artificial Intelligence (StarAI) lab in the Computer Science Department at UCLA. My research interests are in causality (reasoning, inference, discovery), tractable knowledge representations (logical and probabilistic circuits), and machine learning.

Previously, I was a research fellow at the Simons Institute for the Theory of Computing at UC Berkeley, and received my DPhil in Computer Science from the University of Oxford under the supervision of Prof. Marta Kwiatkowska.

Experience

  • Postdoctoral Scholar

    January 2024 - Present

    UCLA

  • Research Fellow

    August 2023 - December 2023

    Simons Institute, UC Berkeley

  • Research Intern

    June 2023 - August 2023

    Microsoft Research Cambridge

Education

  • DPhil in Computer Science, 2023

    University of Oxford

  • MSc in Statistics, 2019

    University of Oxford

  • BA in Mathematics, 2018

    University of Cambridge

Recent Publications

Quickly discover relevant content by filtering publications.
Benjie Wang, Denis Deratani Mauá, Guy Van den Broeck, YooJung Choi (2024). A Compositional Atlas for Algebraic Circuits. Conference on Neural Information Processing Systems (NeurIPS).

Cite

Renato Lui Geh, Honghua Zhang, Kareem Ahmed, Benjie Wang, Guy Van den Broeck (2024). Where is the signal in tokenization space?. Conference on Empirical Methods in Natural Language Processing (EMNLP).

Cite URL

Benjie Wang, Joel Jennings, Wenbo Gong (2024). Neural Structure Learning with Stochastic Differential Equations. International Conference on Learning Representations (ICLR).

Cite URL

Xiyue Zhang, Benjie Wang, Marta Kwiatkowska (2024). Provable Preimage Under-Approximation for Neural Networks. International Conference on Tools and Algorithms for the Construction and Analysis of Systems (TACAS).

Cite URL

Benjie Wang, Marta Kwiatkowska (2023). Compositional Probabilistic and Causal Inference using Tractable Circuit Models. International Conference on Artificial Intelligence and Statistics (AISTATS).

Cite URL

See all publications

Contact