Shivvrat Arya
Assistant Professor, Computer Science
- shivvrat.arya@njit.edu
- 973-596-2318
- 4304 Guttenberg Information Technologies Center (GITC)
About Me
Shivvrat Arya is the Director of the Algorithms and Architectures for Reasoning and Intelligent Automation (ARIA) Lab. He earned his Ph.D. in Computer Science from The University of Texas at Dallas, where he was advised by Vibhav Gogate and Yu Xiang.
His research focuses on interpretable, trustworthy, and efficient artificial intelligence, with an emphasis on neurosymbolic reasoning, probabilistic inference, and learning-based methods for combinatorial and constrained optimization. He develops neural and hybrid AI systems that integrate structured knowledge with data-driven learning for reliable decision-making in complex environments. His work spans neural inference, structured reasoning, and optimization, with applications in computer vision, video understanding, multimodal reasoning, and human-centered AI. His research has received Best Paper recognition and Spotlight and Oral distinctions at major AI venues, including NeurIPS and AAAI.
He is recruiting motivated PhD, MS, and undergraduate students. Hiring details are available at https://aria-research-lab.github.io/hiring/.
His research focuses on interpretable, trustworthy, and efficient artificial intelligence, with an emphasis on neurosymbolic reasoning, probabilistic inference, and learning-based methods for combinatorial and constrained optimization. He develops neural and hybrid AI systems that integrate structured knowledge with data-driven learning for reliable decision-making in complex environments. His work spans neural inference, structured reasoning, and optimization, with applications in computer vision, video understanding, multimodal reasoning, and human-centered AI. His research has received Best Paper recognition and Spotlight and Oral distinctions at major AI venues, including NeurIPS and AAAI.
He is recruiting motivated PhD, MS, and undergraduate students. Hiring details are available at https://aria-research-lab.github.io/hiring/.
Education
Ph.D.; THE UNIVERSITY OF TEXAS AT DALLAS, RICHARDSON, TEXAS; Computer Science; 2025
M.S.; THE UNIVERSITY OF TEXAS AT DALLAS, RICHARDSON, TEXAS; Computer Science; 2021
B.Tech.; INDIAN INSTITUTE OF INFORMATION TECHNOLOGY VADODARA, INDIA; Computer Science and Engineering; 2019
Awards & Honors
Website
2026 Fall Courses
DS 488 - INDEPENDENT STUDY IN DS
CS 370 - INTRO TO ARTIFCL INTELLGNCE - HONORS
CS 725 - INDEPENDENT STUDY I
CS 726 - INDEPENDENT STUDY II
CS 790A - DOCT DISSERTATION & RES
CS 700B - MASTER'S PROJECT
CS 792 - PRE-DOCTORAL RESEARCH
CS 701B - MASTER'S THESIS
CS 488 - INDEPENDENT STUDY IN CS
CS 489 - COMPUTER SCIENCE RESEARCH PROJ
Past Courses
Research Interests
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.
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.
Other
Journal Article
Conference Proceeding