Kiran Purohit

Kiran Purohit

Research Scholar

IIT Kharagpur

Biography

I am currently pursuing my Ph.D. in the Department of Computer Science and Engineering at IIT Kharagpur, under the supervision of Prof. Sourangshu Bhattacharya. I am also a member of the Complex Networks Research Group.

Research - I am broadly interested in Machine Learning, with specific interests in Scalability, Explainability and Data-centric AI. I have applied these techniques on problems in Computer Vision and Natural Language Processing. My research involves subset selection for efficient and robust deep learning. I would be happy to talk about recent advancements around LLMs.

Interests

  • Machine Learning
  • Data-centric AI
  • Subset Selection
  • Scalable AI
  • Trustworthy AI
  • Explainable AI

Education

  • PhD in Computer Science and Engineering, 2020 - Present

    Indian Institute of Technology Kharagpur

  • M.Tech in Computer Science and Engineering, 2018 - 2020

    National Institute of Technology Durgapur

Publications

List of all publications till date

Quickly discover relevant content by filtering publications.

EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning

Answering reasoning-based complex questions over text and hybrid sources, including tables, is a challenging task. Recent advances in …

A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs

Deep convolutional neural networks (CNNs) have achieved impressive performance in many computer vision tasks. However, their large …

A Data-Driven Defense against Edge-case Model Poisoning Attacks on Federated Learning

Federated Learning systems are increasingly subjected to a multitude of model poisoning attacks from clients. Among these, edge-case …

Accurate and efficient channel pruning via orthogonal matching pursuit

The deeper and wider architectures of recent convolutional neural networks (CNN) are responsible for superior performance in computer …

COVID-19 Detection on Chest X-Ray and CT Scan Images Using Multi-image Augmented Deep Learning Model

COVID-19 is a deadly and highly infectious pneumonia type disease. RT-PCR is a proven testing methodology for the detection of …

Recent Talks

Application of Subset Selection in Efficient Machine Learning @IBM Maitreyee Research Showcase 2024

Deep convolutional neural networks (CNNs) have achieved impressive performance in many computer vision tasks. However, their large …

A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs @TMLR 2024

Deep convolutional neural networks (CNNs) have achieved impressive performance in many computer vision tasks. However, their large …

When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories @CNeRG Reading Group

Despite their impressive performance on diverse tasks, large language models (LMs) still struggle with tasks requiring rich world …

Scalable and Accurate Channel pruning @CNeRG Mini Retreat

The deeper and wider architectures of recent convolutional neural networks (CNN) are responsible for superior performance in computer …

Winning the Lottery Ahead of Time: Efficient Early Network Pruning @CNeRG Reading Group

Pruning, the task of sparsifying deep neural networks, received increasing attention recently. Although state-of-the-art pruning …

Experience

Intern and Job Experiences

 
 
 
 
 

Ph.D. Research Scholar

CNeRG Lab, CSE Department, IIT Kharagpur

Sep 2020 – Present Kharagpur, West Bengal
Under the Supervision of Prof. Sourangshu Bhattacharya
 
 
 
 
 

M.Tech

NIT Durgapur

Aug 2018 – May 2020 Durgapur, West Bengal
M.Tech in Computer Science and Technology
 
 
 
 
 

Trainee

DRDO Dehradun, Uttrakhand

Jun 2016 – Jul 2016 Dehradun, Uttrakhand

NETWORK DOCKET MANAGEMENT SYSTEM

Responsibilities include:

  • Understaning ASP and Oracle.
  • Developing a website for automation of complaints registered.

Contact

  • CNeRG Lab, CSE Department, IIT Kharagpur, Kharagpur, West Bengal 721302
  • Enter CSE Dept and take the stairs to Room 205 on 1st Floor
  • Weekdays from 10:00 am to 5:00 pm
  • Book an appointment
  • DM Me