StepIdeator: Utilizing Mixed Representations to Support Step-by-step Design With Generative AI

J Yao, P Chen, Z Li, Y Cai, Y Wu… - Journal of …, 2024 - asmedigitalcollection.asme.org
In product conceptual design, designers utilize multiple design representations to iteratively
ideate, externalize, and refine concepts. Mixed representations, defined as the simultaneous …

From Language to Pixels: Task Recognition and Task Learning in LLMs

J Falkenstein, C Schuster, A Berger… - Proceedings of the 2nd …, 2024 - aclanthology.org
LLMs can perform unseen tasks by learning from a few in-context examples. How in-context
learning works is still uncertain. We investigate the mechanisms of in-context learning on a …

Enhancing a Probabilistic Auto-regressive Model with Gaussian Noise and Savitzky–Golay Filter for the Data Generation of Small-Scale Education Datasets

KT Chui, JTW Chan, R Yousuk, LK Lee… - … on Technology in …, 2024 - Springer
Sufficient samples are important to train accurate and robust machine learning models. In
education datasets, common applications, including learning analytics, innovative learning …

[PDF][PDF] The Art of Prompting: Unleashing the Power of Large Language Models

A Thakur - researchgate.net
This research provides a comprehensive guide to prompting, a technique that leverages the
power of large language models (LLMs) to perform various natural language tasks …