This was a great collaboration with Walter Simoncini (equal contribution), Tijmen Blankevoort, @cgmsnoek.bsky.social and @yukimasano.bsky.social
Website: elastic.ashita.nl
Paper: arxiv.org/abs/2510.17700
Code: github.com/WalterSimonc...
arxiv.org
Elastic ViTs from Pretrained Models without Retraining
Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes, forcing sub-optimal deployment choices under real-world constraints. We introdu...
