🎓 Shivvrat Arya has joined the Department of Computer Science at the Ying Wu College of Computing, New Jersey Institute of Technology (NJIT) as a Tenure-Track Assistant Professor.
📢 He is currently recruiting motivated Ph.D. students (Spring & Fall 2026) as well as undergraduate and master’s students interested in research opportunities.
Biography
Shivvrat Arya is an Assistant Professor of Computer Science at the Ying Wu College of Computing, New Jersey Institute of Technology (NJIT). He received his Ph.D. in Computer Science from the University of Texas at Dallas, where he worked with Dr. Vibhav Gogate and Dr. Yu Xiang.
His research lies at the intersection of Artificial Intelligence and Machine Learning, with emphasis on neuro-symbolic AI, probabilistic reasoning, explainable AI, and combinatorial optimization. The overarching goal of his work is to develop interpretable and trustworthy AI systems that combine structured domain knowledge with powerful data-driven learning. His research spans graph-based inference and symbolic reasoning, with applications in computer vision and natural language processing, particularly video understanding, activity recognition, and language reasoning.
Research Focus
- Neurosymbolic AI: Integrating formal world models with neural networks
- Probabilistic Methods: Novel inference approaches for graphical models
- Explainable AI: Interpretable models supporting polynomial-time reasoning
- Combinatorial Optimization: Efficient algorithms for NP-hard problems
- Applications: Vision and language tasks including video understanding and activity recognition
Research Highlights
- Published research recognized with best paper awards, spotlight, and oral presentations
- Developed NeuPI, a neural inference engine for probabilistic models
- Built real-time AR guidance systems for complex physical tasks
- Released CaptainCook4D, an egocentric 4D dataset for procedural task understanding
Past Work
Dr. Arya’s doctoral research was supported by several competitive federal grants, including programs from DARPA, the National Science Foundation (NSF), and the Air Force Office of Scientific Research (AFOSR). Major DARPA projects included:
- Explainable Artificial Intelligence (XAI)
- Perceptually-Enabled Task Guidance (PTG)
- Assured Neuro Symbolic Learning and Reasoning (ANSR)
This work advanced methods for explainable reasoning, probabilistic inference, and real-time task guidance, producing award-winning publications and widely used datasets.
Education
- Ph.D., Computer Science – The University of Texas at Dallas
- M.S., Computer Science – The University of Texas at Dallas
- B.Tech., Computer Science and Engineering – IIIT Vadodara
Shivvrat Arya
Our paper, "SINE - Scalable MPE Inference for Probabilistic Graphical Models using Advanced Neural Embeddings" has been accepted for publication in 28th International Conference on Artificial Intelligence and Statistics (AISTATS) 2025.
Recognized as a Top Reviewer (among the top 8% of reviewers) for NeurIPS 2024!
Our paper, "A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models" has been accepted for publication at NeurIPS 2024 as a Spotlight Presentation.