Anusha Nerella leads fintech automation at State Street, focused on Java Engineering, AI and intelligent automation.

Mixture-of-Recursions (MoR) is a new AI architecture that promises to cut LLM inference costs and memory use without ...

Captum is a model interpretability and understanding library for PyTorch. Captum means comprehension in Latin and contains general purpose implementations of integrated gradients, saliency maps, ...

To address AI architecture design challenges, we present an architecture evolution of AI systems in the era of foundation models, transitioning from “foundation-model-as-a-connector” to ...

To realize model IP protection across platforms and environments, we propose a robust hashing scheme for neural network models via heterogeneous graph representation, which can effectively detect the ...

This lack of support forces developers to either compromise on model performance by using a single dtype throughout the module or implement complex and error-prone workarounds to split the module into ...