Elastic ViTs from Pretrained Models without Retraining 事件

Elastic ViTs from Pretrained Models without Retraining arXiv:2510.17700v2 Announce Type: replace Abstract: 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 introduce SnapViT: Single-shot network approximation for pruned Vision Transformers, a new post-pretraining structured pruning method that enables elastic inference across a continuum of compute budg