Rohit Babbar

Senior Lecturer (Associate Professor)
Department of Computer Science
University of Bath, UK
rb2608--AT--bath.ac.uk

Hello, I am a Senior Lecturer (Associate Professor) at the Computer Science department of the University of Bath, UK. With my PhD students, we are working on exciting problems on sparse and memory/energy efficient neural networks for learning in large output spaces and Large Language Models (LLMs). I am also looking for motivated students to join my group at the University of Bath, UK. Please reach out at rb2608--AT--bath.ac.uk, if you are interested in joining!

Research Interests

Artificial Intelligence, Resource-efficient Machine Learning, Learning in large output spaces, AI safety

Recent Publications

• ELMO: Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces.
  Jinbin Zhang, Nasib Ullah, Erik Schultheis, and Rohit Babbar.
  42nd International Conference on Machine Learning, ICML 2025, Vancouver, Canada [PDF] [Code]
• UniDEC: Unified Dual Encoder and Classifier Training for Extreme Multi-Label Classification.
  Siddhant Kharbanda, Devaansh Gupta, Gururaj K, Pankaj Malhotra, Cho-Jui Hsieh, and Rohit Babbar.
  The Web Conference, WebConf 2025, Sydney, Australia [PDF]
• How Well Calibrated are Extreme Multi-label Classifiers? An Empirical Analysis.
  Nasib Ullah, Erik Schultheis, Jinbin Zhang and Rohit Babbar.
  31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2025, Toronto, Canada [PDF] [Code]
• Large Language Model as a Teacher for Zero-shot Tagging at Extreme Scales.
  Nasib Ullah, Jinbin Zhang and Rohit Babbar.
  31st International Conference on Computational Linguistics, COLING, 2025, Abu-Dhabi, UAE [PDF] [Code]
• Navigating Extremes : Dynamic Sparsity in Large Output Spaces.
  Nasib Ullah, Erik Schultheis, Mike Lasby, Yani Ioannou and Rohit Babbar.
  38th Conference on Neural Information Processing Systems, NeurIPS, 2024, Vancouver, Canada [PDF] [Code]
• Gandalf : Learning Label-label correlations in Extreme Multi-label Classification via Label Features. Siddhant Kharbanda, Devaansh Gupta, Erik Schultheis, Atmadeep Banerjee, Cho-Jui Hsieh, and Rohit Babbar
  30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024, Barcelona, Spain [PDF]
• A General Online Algorithm for Optimizing Complex Performance Metrics.
  Wojciech Kotlowski, Erik Schultheis, Marek Wydmuch, Rohit Babbar, and Krzysztof Dembczyński
  41st International Conference on Machine Learning, ICML 2024, Vienna, Austria [PDF] [Code]
• Consistent Algorithms for Multi-label Classification with Macro@k Metrics.
  Erik Schultheis, Marek Wydmuch, Wojciech Kotlowski, Rohit Babbar, Strom Borman, and Krzysztof Dembczyński.
  12th International Conference on Learning Representations, ICLR 2024, Vienna, Austria [PDF] [Code]
• Generalized Test Utilities for Long-tail Performance in Extreme Multi-label Classification.
  Erik Schultheis, Marek Wydmuch, Wojciech Kotlowski, Rohit Babbar, and Krzysztof Dembczyński
  37th Conference on Neural Information Processing Systems, NeurIPS, 2023, New Orleans, USA [PDF][Code]
• Towards Memory-Efficient Training for Extremely Large Output Spaces -- Learning with 500k Labels on a Single Commodity GPU.
  Erik Schultheis, and Rohit Babbar
  ECML-PKDD, 2023, Torino, Italy [PDF][Code]

Teaching

• Foundational Machine Learning (Fall 2025)
• Machine Learning - Foundations and Frontiers (Spring 2025)
• Machine Learning - 1 (Fall 2024)

Contact

Office: Wessex House
Claverton Down
Bath, BA2 7AY, UK