Scholar
Ayush Kumar Tarun
Google Scholar ID: QYJGgtsAAAAJ
EPFL
Citations & Impact
Citations
893
H-index
7
i10-index
6
Publications
13
Co-authors
19
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'Chitrarth: Bridging Vision and Language for a Billion People' accepted at MAR Workshop at NeurIPS; 'Chitranuvad: Adapting Multi-lingual LLMs for Multimodal Translation' accepted at WAT2024 at EMNLP; 'EcoVal: An Efficient Data Valuation Framework for Machine Learning' accepted in KDD 2024; 'Deep Regression Unlearning' accepted in ICML-2023; 'Fast Yet Effective Machine Unlearning' accepted in IEEE TNNLS; 'Zero-Shot Machine Unlearning' accepted in IEEE TIFS; 'TabSynDex: A Universal Metric for Robust Evaluation of Synthetic Tabular Data' accepted in IEEE TAI; 'Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher' accepted in AAAI-2023.
Research Experience
- Joined Krutrim as a Research Scientist in February 2024; joined Famdo as the Lead of AI & Research in July 2023; joined Pepper Content as a Machine Learning Engineer in April 2022; interned as an SDE at Salesforce in June 2021.
Education
- PhD student at EPFL’s NLP Lab, supervised by Prof. Antoine Bosselut; completed B.E. from BITS Pilani, India, with a thesis supervised by Dr. Mohan Kankanhalli and Dr. Murari Mandal at National University of Singapore.
Background
- Deeply captivated by the transformative potential of deep learning and machine learning across diverse domains. Research interests include recommendation systems, computer vision, natural language processing (NLP), and privacy. Currently, his research primarily focuses on multilingual LLMs.
Miscellany
- In free time, enjoys sports, mostly cricket and badminton, playing the piano, and sleeping.
