Scholar
Kiran Purohit
Google Scholar ID: KvaPPWAAAAAJ
Senior Researcher-II @ Fujitsu Research
Citations & Impact
Citations
113
H-index
4
i10-index
1
Publications
8
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- May 2025: Paper on Sample Efficient Demonstration Selection for In-Context Learning accepted at ICML 2025; Sep 2024: Paper on EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning accepted at EMNLP 2024; Aug 2024: Paper on A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs accepted at TMLR 2024; Jul 2024: Paper on A Data-Driven Defense against Edge-case Model Poisoning Attacks on Federated Learning accepted at ECAI 2024; Sep 2022: Paper on Accurate and Efficient Channel pruning via Orthogonal Matching Pursuit accepted at AIMLSystems 2022; Additionally, received multiple conference invitations and awards.
Research Experience
- Engaged in research on Machine Learning, particularly focusing on Scalability, Explainability, and Data-centric AI. Applied these techniques to solve problems in Computer Vision and Natural Language Processing. Research involves subset selection for efficient and robust deep learning.
Education
- PhD in Computer Science and Engineering, 2020 - Present, Indian Institute of Technology Kharagpur, Advisor: Prof. Sourangshu Bhattacharya; M.Tech in Computer Science and Engineering, 2018 - 2020, National Institute of Technology Durgapur.
Background
- Currently pursuing a Ph.D. in the Department of Computer Science and Engineering at IIT Kharagpur, under the supervision of Prof. Sourangshu Bhattacharya. Also a member of the Complex Networks Research Group. Broadly interested in Machine Learning, with specific interests in Scalability, Explainability, and Data-centric AI. Applied these techniques on problems in Computer Vision and Natural Language Processing. Research involves subset selection for efficient and robust deep learning. Interested in recent advancements around LLMs.
Miscellany
- Interested in new developments in the field of Machine Learning, especially around large language models (LLMs).
