Shivvrat Arya is an Assistant Professor of Computer Science at the New Jersey Institute of Technology (NJIT). His research focuses on fast neural solvers for combinatorial optimization and probabilistic inference, enabling efficient reasoning over large networks and reducing inference time from minutes to microseconds. His recent work has advanced neural inference methods, real-time task guidance, and large-scale multimodal data modeling. His contributions have been recognized with Best Paper, Spotlight, and Oral Presentation Awards at major AI conferences.

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

https://shivvrat.github.io/

CS 785 - ST: NEUROSYMBOLIC AI

Neurosymbolic AI;
Learning-Based and Neural Combinatorial Optimization;
Probabilistic Reasoning and Inference;
Interpretable and Trustworthy Machine Learning;
Applications in Computer Vision, Activity Recognition, and Multimodal Understanding.

"Learning to Condition: A Neural Heuristic for Scalable MPE Inference"
arXiv preprint arXiv:2509.25217, 2025.

"SINE: Scalable MPE Inference for Probabilistic Graphical Models using Advanced Neural Embeddings"
2025.

"RELINK: Edge Activation for Closed Network Influence Maximization via Deep Reinforcement Learning"
ACM, November, 2025.

"A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models"
Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2024.

"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities"
Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2024.

Chiradeep Roy, Mahsan Nourani, Shivvrat Arya, Mahesh Shanbhag, Tahrima Rahman, Eric D. Ragan, Nicholas Ruozzi, Vibhav Gogate. 2023. "Explainable Activity Recognition in Videos using Deep Learning and Tractable Probabilistic Models." ACM Transactions on Interactive Intelligent Systems , vol. 13 , no. 4 , pp. 1-32.