Meet P. Vadera

I am an Applied Scientist at Amazon, where I work on post-training and alignment for Rufus, Amazon's AI shopping assistant. Previously, I worked on post-training for large language models that power Alexa+, and also on large-scale deep learning solutions at Alexa Smart Home.

I completed my Ph.D. in Computer Science at the University of Massachusetts Amherst, where I was advised by Benjamin Marlin. My research interests include large language model post-training and alignment, Bayesian deep learning, and robustness in deep learning. I have also worked in the areas of mobile health (mHealth) and medical imaging.

Before joining the Ph.D. program, I worked as a Member of Technical Staff at Innovaccer, where I built products using big-data technologies to help healthcare organizations deliver better care. I earned my Bachelor of Technology (B.Tech.) degree from the Indian Institute of Technology (IIT) Gandhinagar, where I majored in Mechanical Engineering and had a minor in Computer Science and Engineering.

Email  /  CV  /  Google Scholar  /  GitHub  /  Twitter

profile photo
Publications

  1. Uncertainty Quantification Using Query-Based Object Detectors
    Meet P. Vadera, Colin Samplawski, Benjamin M Marlin
    ECCV Workshop on Uncertainty Quantification for Computer Vision, 2022

  2. URSABench: A System for Comprehensive Benchmarking of Bayesian Deep Neural Network Models and Inference methods
    Meet P. Vadera, Jinyang Li, Adam D. Cobb, Brian Jalaian, Tarek Abdelzaher, Benjamin M. Marlin
    Fifth Conference on Machine Learning and Systems (MLSys), 2022

  3. Challenges and Opportunities in Approximate Bayesian Deep Learning for Intelligent IoT Systems
    Meet P. Vadera, Benjamin M. Marlin
    IEEE International Conference on Cognitive Machine Intelligence (CogMI), 2021

  4. Post-hoc loss-calibration for Bayesian Neural Networks
    Meet P. Vadera, Soumya Ghosh, Kenney Ng, Benjamin M. Marlin
    Conference on Uncertainty in Artificial Intelligence (UAI), 2021

  5. On Uncertainty and Robustness in Large-Scale Intelligent Data Fusion Systems
    Benjamin M. Marlin, Tarek Abdelzaher, Gabriela Ciocarlie, Adam D. Cobb, Mark Dennison, Brian Jalaian, Lance Kaplan, Tiffany Raber, Adrienne Raglin, Piyush K. Sharma, Mani Srivastava, Theron Trou, Meet P. Vadera, Maggie Wigness
    IEEE International Conference on Cognitive Machine Intelligence (CogMI), 2020

  6. Generalized Bayesian Posterior Expectation Distillation for Deep Neural Networks
    Meet P. Vadera, Brian Jalaian, Benjamin M. Marlin
    Conference on Uncertainty in Artificial Intelligence (UAI), 2020

  7. URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks
    Meet P. Vadera, Adam D. Cobb, Brian Jalaian, Benjamin M. Marlin
    ICML Workshop on Uncertainty and Robustness in Deep Learning, 2020

  8. Assessing the Adversarial Robustness of Monte Carlo and Distillation Methods for Deep Bayesian Neural Network Classification
    Meet P. Vadera*, Satya Narayan Shukla*, Brian Jalaian, Benjamin M. Marlin
    AAAI Workshop on Artificial Intelligence Safety (SafeAI), 2020

  9. Investigating Fusion-Based Deep Learning Architectures for Smoking Puff Detection
    Meet P. Vadera, Benjamin M. Marlin
    IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), 2019 [Poster paper]

  10. Towards Joint Segmentation and Active Learning for Block-Structured Data Streams
    Conrad Holtsclaw, Meet P. Vadera, Benjamin M. Marlin
    KDD Workshop on Data Collection, Curation, and Labeling (DCCL) for Mining and Learning, 2019 [Best paper award]

  11. Assessing the Robustness of Bayesian Dark Knowledge to Posterior Uncertainty
    Meet P. Vadera, Benjamin M. Marlin
    ICML Workshop on Uncertainty and Robustness in Deep Learning, 2019

  12. Multiclass Diagnosis of Neurodegenerative Diseases: A Neuroimaging Machine-Learning-Based Approach
    Gurpreet Singh, Meet P. Vadera, Lakshminarayanan Samavedham, Erle Chuen-Hian Lim
    ACS Journal of Industrial & Engineering Chemistry Research, 2019

  13. Machine Learning-Based Framework for Multi-Class Diagnosis of Neurodegenerative Diseases: A study on Parkinson's Disease
    Gurpreet Singh, Meet P. Vadera, Erle Chuen-Hian Lim, Lakshminarayanan Samavedham
    IFAC Symposium on Dynamics and Control of Process Systems including Biosystems DYCOPS-CAB, 2016

*Equal contribution.


Website based on Jon Barron's template.