Deep Shankar Pandey
Applied Scientist at Amazon · Trustworthy AI researcher
I’m an Applied Scientist at Amazon, where I work on search and recommendation systems that personalize content discovery for Fire TV customers.
My research is in trustworthy AI: developing models that can learn from limited data and give meaningful estimates of their uncertainty. During my Ph.D., I worked on evidential deep learning, Bayesian methods, and uncertainty-aware meta-learning, with an emphasis on efficient, robust, and well-calibrated few-shot learning.
I’m also interested in large language models and, more broadly, how to make AI systems reliable, adaptable, and useful in the real world.
I earned my Ph.D. in Computing and Information Sciences at Rochester Institute of Technology, where I worked with Prof. Qi Yu. I completed my undergraduate degree in Electronics and Communication Engineering at the Institute of Engineering, Pulchowk Campus in Nepal.
News
| Jun 5, 2026 | Our paper on generalized regularized evidential deep learning appeared in the June 2026 issue of IEEE TPAMI. |
|---|---|
| Feb 2025 | I joined Amazon’s Fire TV Science team as an Applied Scientist, working on search, recommendations, and personalization. |
| Jan 16, 2025 | I defended my Ph.D. dissertation, Uncertainty-Aware Meta-Learning for Learning from Limited Data, at RIT. |
| Dec 10, 2024 | Our work on Bayesian parameter-efficient fine-tuning of vision foundation models appeared at NeurIPS 2024. |
Publications
- TPAMI · 2026Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation
- NeurIPS · 2024Be Confident in What You Know: Bayesian Parameter Efficient Fine-Tuning of Vision Foundation Models
- APL ML · 2024The Development of Thermodynamically Consistent and Physics-Informed Equation-of-State Model Through Machine Learning
- MLST · 2024Deep Energy-Pressure Regression for a Thermodynamically Consistent EOS Model
- ICML · 2023Learn to Accumulate Evidence from All Training Samples: Theory and Practice
- ICML · 2023Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery
- AAAI · 2023Evidential Conditional Neural Processes
- CVPR · 2022Multidimensional Belief Quantification for Label-Efficient Meta-Learning
- Big Data · 2021Uncertainty-Aware Multiple Instance Learning from Large-Scale Long Time Series Data