Pratyush Maini
Publications by Year
Research Areas
Adversarial Robustness in Machine Learning, Natural Language Processing Techniques, Topic Modeling, Explainable Artificial Intelligence (XAI), Advanced Neural Network Applications
Most-Cited Works
- → Adversarial Robustness Against the Union of Multiple Perturbation Models(2019)44 cited
- → Dataset Inference: Ownership Resolution in Machine Learning(2021)23 cited
- → Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling(2024)11 cited
- → Scaling Laws for Data Filtering—Data Curation Cannot be Compute Agnostic(2024)9 cited
- → Understanding Hallucinations in Diffusion Models through Mode Interpolation(2024)8 cited
- → Model-tuning Via Prompts Makes NLP Models Adversarially Robust(2023)7 cited
- → T-MARS: Improving Visual Representations by Circumventing Text Feature Learning(2023)4 cited
- → TOFU: A Task of Fictitious Unlearning for LLMs(2024)4 cited