Research Interests
- Foundations & Methods — Machine (Deep) Learning, Probabilistic Modeling and Inference, Combinatorial Optimization, Neurosymbolic AI, Explainable and Interpretable Models
- Applications — Human–AI Interaction with Neuro-symbolic and Deep Models, Computer Vision, Video Understanding, and Language Reasoning
Current Research Focus
Dr. Arya’s current research focuses on developing neuro-symbolic models that integrate deep neural architectures with symbolic reasoning and probabilistic frameworks; advancing tractable probabilistic modeling to support efficient and scalable inference; creating neural network–based solvers for large-scale combinatorial optimization; and designing methods for explainable AI in structured and hybrid systems, with applications in computer vision, activity recognition, and multimodal learning.
Inference in Probabilistic Models
Neural Network-Based Inference
| Title | Venue |
|---|---|
| SINE - Scalable MPE Inference for Probabilistic Graphical Models using Advanced Neural Embeddings | AISTATS'25 |
| A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models | NeurIPS'24-Spotlight UAI TPM'24-Best Paper Award |
| Learning to Solve the Constrained Most Probable Explanation Task | AISTATS'24 UAI TPM'24 |
| Neural Network Approximators for Marginal MAP Inference | AAAI'24-Oral |
Optimization-based Inference Schemes
| Title | Venue |
|---|---|
| Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification | AISTATS'24 |
Video Understanding and Activity Recognition
| Title | Venue |
|---|---|
| CaptainCook4D Dataset | NeurIPS'24 DMLR'23 |
| Explainable Activity Recognition | TiiS'23 |
| Predictive Task Guidance in Augmented Reality | IEEE VR'24 Poster |
Multi-Label Classification
| Title | Venue |
|---|---|
| Kernelized Random Vector Functional Link Network | IJCNN'20 |
Certificates & Awards
