collaborators

5 papers

cs.LG2025

Open Problems in Machine Unlearning for AI Safety

Fazl Barez, Tingchen Fu, Ameya Prabhu +16

As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research, and healthcare, ensuring their safety…

cs.LG2024

Efficient Lifelong Model Evaluation in an Era of Rapid Progress

Ameya Prabhu, Vishaal Udandarao, Philip Torr +3

Standardized benchmarks drive progress in machine learning. However, with repeated testing, the risk of overfitting grows as algorithms over-exploit benchmark idiosyncrasies. In ou…

cs.CV2024

Random Representations Outperform Online Continually Learned Representations

Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru +3

Continual learning has primarily focused on the issue of catastrophic forgetting and the associated stability-plasticity tradeoffs. However, little attention has been paid to the e…

cs.CV2024

No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance

Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh +5

Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for…

cs.LG2024

Corrective Machine Unlearning

Shashwat Goel, Ameya Prabhu, Philip Torr +2

Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do i…