Scholar
Rohit Babbar
Google Scholar ID: QsqvuGsAAAAJ
University of Bath, UK
Citations & Impact
Citations
1,349
H-index
14
i10-index
21
Publications
20
Co-authors
50
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers on topics such as efficiency via low-precision and peak memory optimization in large output spaces, unbiased loss functions for multilabel classification with missing labels, unified dual encoder and classifier training for extreme multi-label classification, how well calibrated are extreme multi-label classifiers, large language model as a teacher for zero-shot tagging at extreme scales, navigating extremes: dynamic sparsity in large output spaces, learning label-label correlations in extreme multi-label classification via label features, a general online algorithm for optimizing complex performance metrics, consistent algorithms for multi-label classification with macro@k metrics, generalized test utilities for long-tail performance in extreme multi-label classification, towards memory-efficient training for extremely large output spaces -- learning with 500k labels on a single commodity GPU.
Research Experience
- Working on exciting problems on sparse and memory/energy efficient neural networks for learning in large output spaces and Large Language Models (LLMs) with PhD students.
Background
- Senior Lecturer (Associate Professor) at the Computer Science department of the University of Bath, UK. Research interests include Artificial Intelligence, Resource-efficient Machine Learning, Learning in large output spaces, and AI safety.
Miscellany
- Teaching Foundational Machine Learning (Fall 2025), Machine Learning - Foundations and Frontiers (Spring 2025), Machine Learning - 1 (Fall 2024).
