Publications

2025

1. arXiv

   Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution

   Muhammad Umair Haider, Hammad Rizwan, Hassan Sajjad, and 2 more authors

   Under Review, 2025

   PDF
2. ICML

   Resolving Lexical Bias in Model Editing

   Hammad Rizwan, Domenic Rosati, Ga Wu, and 1 more author

   Proceedings of the 42nd International Conference on Machine Learning (ICML 2025), 2025

   PDF
3. arXiv

   Instance-Level Difficulty: A Missing Perspective in Machine Unlearning

   Hammad Rizwan, Mahtab Sarvmaili, Hassan Sajjad, and 1 more author

   arXiv preprint arXiv:2410.03043, 2025

   PDF

2022

1. LREC

   Exploring Data Augmentation Strategies for Hate Speech Detection in Roman Urdu

   Ubaid Azam, Hammad Rizwan, and Asim Karim

   In Proceedings of the Thirteenth Language Resources and Evaluation Conference, LREC 2022, Marseille, France, 20-25 June 2022, 2022

   PDF

2020

1. EMNLP

   Hate-Speech and Offensive Language Detection in Roman Urdu

   Hammad Rizwan, Muhammad Haroon Shakeel, and Asim Karim

   In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, 2020

   PDF