Welcome!

I am Shivvrat Arya, but feel free to call me Shiv (pronounced as [ sh ih v ]). I am currently engaged in collaborative research projects under the guidance of Dr. Vibhav Gogate and Dr. Yu Xiang, funded by the DARPA Explainable Artificial Intelligence (XAI), DARPA Perceptually-Enabled Task Guidance (PTG) and DARPA Assured Neuro Symbolic Learning and Reasoning (ANSR) grants. Our goal is to develop AI technology that guides users in the performance of cognitively challenging physical tasks, leveraging breakthroughs in machine perception, automated reasoning, and augmented reality.

My research integrates probabilistic graphical models with deep learning for computer vision tasks, emphasizing tractable probabilistic modeling and neuro-symbolic AI. I’ve developed novel neural network-based inference methods for probabilistic graphical models and explored advanced inference schemes for multi-label classification. These works have been recognized with best paper awards, spotlight and oral presentations.

In video understanding, I’ve contributed to the development of pipelines and datasets for egocentric procedural error recognition, developed explainable models for human activity recognition, and explored predictive task guidance in augmented reality. My earlier work introduced innovative approaches to multi-label classification problems.

This research builds upon my previous work at IIT Indore, where I focused on non-iterative neural network architectures for multi-label classification challenges across diverse datasets.

About me

I am a Ph.D. candidate in the Department of Computer Science at The University of Texas at Dallas, where I am honing my research skills to address complex problems in Computer Science and contribute to the advancement of innovative technologies. I am always on the lookout for challenging opportunities that push the boundaries of my knowledge and allow me to acquire new skills.

In addition to my Ph.D., I am also pursuing an M.S. degree in Computer Science at UT Dallas, working closely with Dr. Vibhav Gogate and Dr. Yu Xiang. I hold a B.Tech. Degree in Computer Science and Engineering from the Indian Institute of Information Technology Vadodara.

Shivvrat Arya

  • B.Tech. CSE, IIITV
  • (Pursuing) M.S. CS, UTD
  • (Pursuing) Ph.D. CS, UTD

News

26 September, 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.

26 September, 2024

Our paper, "CaptainCook4D A Dataset for Understanding Errors in Procedural Activities," has been accepted for publication at NeurIPS 2024 (D&B Track).

19 July, 2024

Our paper "A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models" was recognized with the Best Paper Award at TPM 2024.

22 June, 2024

Our paper "A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models" was accepted for publication in TPM 2024.

22 June, 2024

Our paper "Neural Network Approximators for Marginal MAP in Probabilistic Circuits" was accepted for publication in TPM 2024.

... see all News