Urmish Thakker

TL;DR: This article developed a system for easily mapping general natural language tasks into a human-readable prompted form, and fine-tuned a pretrained encoder-decoder model on this multitask mixture covering a wide variety of tasks.

TL;DR: This survey article proposes to answer the question: how to train distributed machine learning models for resource-constrained IoT devices, and highlights an overview of FL and provides a comprehensive survey of the problem statements and emerging challenges.

TL;DR: PromptSource addresses the emergent challenges in this new setting with a templating language for defining data-linked prompts, an interface that lets users quickly iterate on prompt development by observing outputs of their prompts on many examples, and a community-driven set of guidelines for contributing new prompts to a common pool.

TL;DR: The current landscape of TinyML is presented and the challenges and direction towards developing a fair and useful hardware benchmark for TinyML workloads are discussed, along with three preliminary benchmarks and the selection methodology are discussed.