Naman Jain

I am a research fellow at Microsoft Research, India (MSR) where I work at the intersection of programming languages and machine learning. I am particularly interested in how machine learning techniques can be used for developer productivity tools like program analysis, synthesis, and repair (ML for PL). I am excited about how logic and program synthesis ideas can help be used in machine learning for designing better generalizing, explainable algorithms (PL for ML).

At MSR, I am working with Nagarajan Natarajan, Sriram Rajamani, Prateek Jain, Arun Iyer, Rahul Sharma, and Suresh Parthasarthy. Before that I got my bachelors degree in Computer Science from IIT Bombay where I completed my undergraduate thesis with Prof. Sunita Sarawagi on robustness in natural language processing and also worked with Prof. Arjun Jain in Human Pose Estimation.

/ / / / /


News

Dec 2021 Jigsaw (combining program synthesis with large language models) has been accepted at ICSE'22
Oct 2021 Preprint out on learning decision trees with bandit feedback
Aug 2020 Joined Microsoft Research, India as a Research Fellow
May 2020 Work on named entity robust NLP models accepted in RepL4NLP, ACL'20
Jun 2019 Visiting University of Maryland for research internship with Prof. Abhinava Shrivastava
May 2019 Work on adversarial examples in human pose estimation accepted in VUHCS, CVPR'19
Dec 2018 Recieved Undergraduate Research Award (URA) from IIT Bombay

Research

game

Jigsaw: Large Language Models meet Program Synthesis
Naman Jain, Skanda Vaidyanath, Arun Iyer, Nagarajan Natarajan, Suresh Parthasarathy, Sriram Rajamani, Rahul Sharma
ICSE, 2022

pdf / arxiv / bibtex
@article{jigsaw,
  title={Jigsaw: Large Language Models meet Program Synthesis},
  author={Naman Jain and Skanda Vaidyanath and Arun Iyer and Nagarajan Natarajan and Suresh Parthasarathy and Sriram Rajamani and Rahul Sharma},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.07567}
}

game

Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent
Ajaykrishna Karthikeyan*, Naman Jain*, Nagarajan Natarajan, Prateek Jain
Submitted to AISTATS, 2022

pdf / arxiv / bibtex
@article{banditdgt,
  title={Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent},
  author={Ajaykrishna Karthikeyan and Naman Jain and Nagarajan Natarajan and Prateek Jain},
  booktitle = {ICSE'22},
  month = {May},
  year = {2022}
}
            

game

What’s in a Name? Are BERT Named Entity Representations just as Good for any other Name?
Sriram Balasubramanian*, Naman Jain*, Gaurav Jindal*, Abhijeet Awasthi, Sunita Sarawagi
Workshop On Representation Learning for NLP at ACL, 2020

pdf / arxiv / bibtex
@inproceedings{balasubramanian-etal-2020-whats,
  title = "What{'}s in a Name? Are {BERT} Named Entity Representations just as Good for any other Name?",
  author = "Balasubramanian, Sriram  and Jain, Naman  and Jindal, Gaurav  and Awasthi, Abhijeet  and Sarawagi, Sunita",
  booktitle = "Proceedings of the 5th Workshop on Representation Learning for NLP",
  month = jul,
  year = "2020",
  publisher = "Association for Computational Linguistics",
}
            

game

On the Robustness of Human Pose Estimation
Naman Jain*, Sahil Shah*, Abhishek Sharma, Arjun Jain
Workshop On Augmented Human: Human-centric Understanding at CVPR, 2019

pdf / arxiv / bibtex
@InProceedings{Jain_2019_CVPR_Workshops,
  author = {Jain, Naman and Shah, Sahil and Kumar, Abhishek and Jain, Arjun},
  title = {On the Robustness of Human Pose Estimation},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  month = {June},
  year = {2019}
}
            

Website template stolen from Georgia Gkioxari (and second-hand borrowed from Jon Barron)