Biography and expertise
Dr. Parth Padalkar is a tenure-track Assistant Professor of Computer Science at Texas State University. He received his Ph.D. (2026) and M.S. (2020) in Computer Science from the University of Texas at Dallas and his B.Tech. (2019) in Instrumentation and Control Engineering from the National Institute of Technology Jalandhar, India.
Prior to joining Texas State University, he conducted research at the University of Texas at Dallas and IBM Research, working on neuro-symbolic artificial intelligence, explainable machine learning, and reliable large language models.
His research focuses on developing interpretable and trustworthy AI systems by integrating neural learning with symbolic reasoning. His work spans knowledge representation, logic programming, computer vision, natural language understanding, and intelligent decision-making, with an emphasis on improving the reliability and explainability of AI systems.
Prior to joining Texas State University, he conducted research at the University of Texas at Dallas and IBM Research, working on neuro-symbolic artificial intelligence, explainable machine learning, and reliable large language models.
His research focuses on developing interpretable and trustworthy AI systems by integrating neural learning with symbolic reasoning. His work spans knowledge representation, logic programming, computer vision, natural language understanding, and intelligent decision-making, with an emphasis on improving the reliability and explainability of AI systems.
Education
Doctorate Degree
PhD in Computer Science
University of Texas at Dallas, 2026
Master's Degree
MS in Computer Science
University of Texas at Dallas, 2025
Teaching Interests
Research Interests
Intellectual Property
Copyrights
- “Software for Efficient Matrimonial Match-making”, Govt. of India (Ref no: SW-12849/2019)
- “Software for Identifying Cause and Effect Relationships Between Enablers and Barriers in Sustainable Manufacturing”, Govt. of India (Ref no: SW-10923/2018)

Featured scholarly/creative works
- Padalkar, P., Lee, J., Wei, S., & Gupta, G. (2026). Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters. In 20th International Conference on Neurosymbolic Learning and Reasoning (NeSy 2026). Retrieved from https://arxiv.org/abs/2501.16677
- Lee, P. H., & Padalkar, P. (2026). SpIn-ViT: Designing a Sparsity-Induced Vision Transformer That Is Mechanistically Interpretable. https://doi.org/10.48550/arXiv.2608.14922
- Lahiri, S., Wang, H., Padalkar, P., & Gupta, G. (2025). Explainable AI Tools Provide Meaningful Insight into Rationale for Prediction in Machine Learning Models. Journal of Emerging Investigators. https://doi.org/10.59720/23-341
- Padalkar, P., & Gupta, G. (2025). Symbolic Rule Extraction from Attention-Guided Sparse Representations in Vision Transformers. Theory and Practice of Logic Programming, 25(4), 722--738. https://doi.org/10.1017/S1471068425100318
- Zeng, Y., Rajasekharan, A., Padalkar, P., Basu, K., Arias, Joaqu\’in, & Gupta, G. (2024). Automated Interactive Domain-Specific Conversational Agents that Understand Human Dialogs. In Practical Aspects of Declarative Languages (PADL 2024) (Vol. 14512, pp. 204--222). Springer. https://doi.org/10.1007/978-3-031-52038-9_13
Featured awards
- Award / Honor Recipient: Outstanding graduate Student Award, The University of Texas at Dallas. 2026
- Award / Honor Recipient: University-wide 3 Minute Thesis (3MT) Competition- Finalist, The University of Texas at Dallas. 2025
- Award / Honor Nominee: Best Student Paper Award, International Conference on Logic Programming (ICLP). 2024

Featured service activities
- Member
Resource Committee
