Bokun Wang

Postdoctoral Researcher at UT Austin

I am a Postdoctoral Fellow in the Department of Electrical and Computer Engineering (ECE) at The University of Texas at Austin, working with Prof. Diana Marculescu and the EnyAC group. Before that, I received my Ph.D. degree in Computer Science at Texas A&M University, advised by Prof. Tianbao Yang.

My research interest lies in Efficient Generative AI (Memory | Compute | Data).

Email: bokun.wang@utexas.edu

Research

Theory-driven Efficient Algorithms for SSL

This project focuses on developing efficient algorithms for (multi-modal) self-supervised representation learning (SSL) with convergence and generalization guarantees.

GloFND DPM SOX LibAUC

Efficient Algorithms for Imbalanced and Multi-Instance Medical Image Analysis

Designed memory-efficient and provably convergent algorithms for high-resolution, imbalanced, and multi-instance medical imaging data classification.

MIDAM SOPA

Recent Publications (Full List)

Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning.

Vicente Balmaseda, Bokun Wang, Ching-Long Lin, and Tianbao Yang

In Proceedings of the Forty-second International Conference on Machine Learning (ICML), 2025.

[PDF] [Code] [Poster]

On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning

Bokun Wang, Yunwen Lei, Yiming Ying, and Tianbao Yang

In Proceedings of International Conference on Learning Representations (ICLR), 2025.

[PDF] [Code] [Slides]

Teaching

Guest Lecturer, CSCE 689: Optimization for Machine Learning (Fall 2023), Texas A&M University.
Teaching Assistant, ECS 32B: Introduction to Data Structures (Winter 2020), University of California Davis.
Teaching Assistant, ECS 154A: Computer Architecture (Fall 2019), University of California Davis.
Teaching Assistant, ECS 170: Introduction to Artificial Intelligence (Spring 2019), University of California Davis.
Teaching Assistant, ECS 271: Machine Learning and Data Discovery (Winter 2019), University of California Davis.