I received my Ph.D. in Computer Science from the Department of Electrical Engineering and Computer Science at the University of Arkansas in May 2026, advised by Dr. Xintao Wu.

My research focuses on trustworthy machine learning, with an emphasis on privacy and unlearning. I mainly work on large language (vision) models and graph-structured data. I am also broadly interested in graph foundation models and applications of LLMs on graph data. Currently, I am also working on applications of graph machine learning in physical systems such as critical infrastructure networks.

📝 Preprints

• How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluation [Paper]
  Eduardo Tenorio, Karuna Bhaila, Xintao Wu
  ArXiv 2026

• Cross-Modal Attention Guided Unlearning in Vision-Language Models [Paper]
  Karuna Bhaila, Aneesh Komanduri, Minh-Hao Van, Xintao Wu
  ArXiv 2025 *Also at NeurIPS 2025 Lock-LLM Workshop

📝 Publications

• CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Models [Paper] [Code]
  Aneesh Komanduri, Karuna Bhaila, Xintao Wu
  Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), Main

• Fair In-Context Learning via Latent Concept Variables [Paper] [Code]
  Karuna Bhaila, Minh-Hao Van, Kennedy Edemacu, Chen Zhao, Feng Chen, Xintao Wu
  Proceedings of 2025 IEEE International Conference on Big Data

• Soft Prompting for Unlearning in Large Language Models [Paper] [Code]
  Karuna Bhaila, Minh-Hao Van, Xintao Wu
  Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), Main (Oral)

• DP-TabICL: In-Context Learning with Differentially Private Tabular Data [Paper]
  Alycia N. Carey*, Karuna Bhaila*, Kennedy Edemacu, Xintao Wu
  Proceedings of 2024 IEEE International Conference on Big Data

• Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach [Paper] [Code]
  Karuna Bhaila, Wen Huang, Yongkai Wu, Xintao Wu
  Proceedings of the 2024 SIAM International Conference on Data Mining (SDM)
  *Also at NeurIPS 2023 Workshop New Frontiers in Graph Learning (GLFrontiers)

• Cascading Failure Prediction in Power Grid Using Node and Edge Attributed Graph Neural Networks [Paper] [Code]
  Karuna Bhaila, Xintao Wu
  Proceedings of the 2024 International Joint Conference on Neural Networks (IJCNN)
  *Also at AAAI 2024 Workshop on AI to Accelerate Science and Engineering (AI2ASE)

• Randomized Response Has No Disparate Impact on Model Accuracy [Paper] [Code]
  Alycia N. Carey, Karuna Bhaila, Xintao Wu
  Proceedings of 2023 IEEE International Conference on Big Data

• Fair Collective Classification in Networked Data [Paper]
  Karuna Bhaila, Yongkai Wu, Xintao Wu
  Proceedings of 2022 IEEE International Conference on Big Data
  *Also at KDD 2022 Workshop on Ethical Artificial Intelligence: Methods and Applications (EAI-KDD)

🎖 Honors and Awards

• GSIE Presentation Travel Grant (NAACL 2025, NeurIPS 2025)
• Margaret Gerig Martin Graduate Scholarship
• SIAM 2024 Student Travel Award
• Reginald R. ‘Barney’ & Jameson A. Baxter Graduate Fellowship
• College of Engineering Graduate Fellowship
• Webster International Scholarship

💻 Experience

• 2025.05 - 2025.08: InfoSec Research Intern, Walmart Global Tech
• 2019.05 - 2020.05: Data Analyst, Faculty Development Center at Webster University
• 2019.05 - 2019.07: Intern, Jenzabar

💬 Teaching

• Teaching Assistant, Programming Foundations II
  Undergraduate course, University of Arkansas, 2025
• Guest Lecturer, Data Mining
  Undergraduate course, University of Arkansas, 2023 - 2025
• Lecturer, Python and Machine Learning
  Multidisciplinary Bootcamp (MDaS), University of Arkansas, 2021 - 2024
• Math and CS Tutor
  Webster University, 2019 - 2020

💻 Services

Conference Reviewer

• Conference on Language Modeling (COLM)
• Learning on Graphs Conference (LoG)
• AAAI Conference on Artificial Intellligence (AAAI)
• Asian Conference on Machine Learning (ACML)
• Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)
• International Conference on Machine Learning and Applications (ICMLA)
• International Joint Conference on Neural Networks (IJCNN)

Journal Reviewer

• Transactions on Knowledge and Data Engineering (TKDE)
• Transactions on Big Data (TBD)
• International Journal of Data Science and Analytics (IJDSA)
• Human-Centric Intelligent Systems (HCIN)
• Transactions on Intelligent Systems and Technology (TIST)

Workshop Reviewer

• KDD Workshop on Ethical Artificial Intelligence: Methods and Applications (EAI-KDD)