New Preprints Online!

20 October 2023, by DS Group

We have two new pre-prints available online which explore methodological foundations of (multimodal) large pretrained models.

“ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale”

M Frohmann, C Holtermann, S Masoudian, A Lauscher, N Rekabsaz

arXiv preprint arXiv:2310.01217, available here.

AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ

J Belouadi, A Lauscher, S Eger

arXiv preprint arXiv:2310.00367, available here.