Biography

Shivvrat Arya is an Assistant Professor of Computer Science at the Ying Wu College of Computing, New Jersey Institute of Technology (NJIT), where he also serves as the Director of the ARIA Lab. He earned his Ph.D. in Computer Science from the University of Texas at Dallas under the supervision of Vibhav Gogate and Yu Xiang.

His research advances interpretable and trustworthy AI through two complementary directions:

1. Probabilistic reasoning, neurosymbolic AI, and explainable AI, applied to real-world problems in computer vision and natural language processing, and
2. Combinatorial and constrained optimization, with an emphasis on learning-based and neural approaches.

Dr. Arya’s work develops AI systems that integrate structured domain knowledge with data-driven learning. His contributions span graph-based inference, symbolic reasoning, and neural solvers for optimization, with applications in video understanding, activity recognition, and multimodal reasoning.

Research Focus

• Neurosymbolic AI & Explainable Systems: Integrating symbolic structure with deep learning for transparent reasoning. We develop hybrid architectures that combine neural pattern recognition with logical inference for interpretable decision-making.
• Neural Combinatorial Optimization: Learning-based solvers for combinatorial and constrained problems. Our work explores neural architectures that learn to solve NP-hard optimization problems efficiently.
• Deep Reinforcement Learning for Graph Optimization: Graph neural networks combined with reinforcement learning for solving complex graph-based optimization problems, including routing, scheduling, and resource allocation.
• Probabilistic Inference: Scalable neural methods for reasoning under uncertainty. We develop efficient algorithms for probabilistic graphical models and neural approaches to approximate inference.
• Applications of Neurosymbolic Methods: Computer vision, video understanding, activity recognition, human-computer interaction, and multimodal reasoning. Applying neurosymbolic AI to real-world tasks requiring structured understanding.

Research Highlights

• Publications recognized with best paper awards, spotlights, and oral presentations at top AI/ML venues
• Developed NeuPI, a neural inference engine that accelerates probabilistic reasoning from minutes to microseconds
• 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 competitive federal grants from DARPA, the National Science Foundation (NSF), and the Air Force Office of Scientific Research (AFOSR). Major DARPA programs included:

• Explainable Artificial Intelligence (XAI)
• Perceptually-Enabled Task Guidance (PTG)
• Assured Neuro Symbolic Learning and Reasoning (ANSR)

This work advanced explainable reasoning, probabilistic inference, and real-time task guidance, resulting in 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 ng – IIIT Vadodara