Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney

1 code implementation • 20 Nov 2023 • Shachar Don-Yehiya, Leshem Choshen, Omri Abend

Generating images with a Text-to-Image model often requires multiple trials, where human users iteratively update their prompt based on feedback, namely the output image.

ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning

no code implementations • 2 Dec 2022 • Shachar Don-Yehiya, Elad Venezian, Colin Raffel, Noam Slonim, Yoav Katz, Leshem Choshen

We propose a new paradigm to continually evolve pretrained models, denoted ColD Fusion.

PreQuEL: Quality Estimation of Machine Translation Outputs in Advance

1 code implementation • 18 May 2022 • Shachar Don-Yehiya, Leshem Choshen, Omri Abend

We show that this augmentation method can improve the performance of the Quality-Estimation task as well.

Data Augmentation Machine Translation +2