Your Transformer Is Secretly Elastic
A retraining-free method turns transformers into elastic models that prune smoothly up to 60% sparsity.
Stories per day · 30 days
2 RSS
Relatedelastic-inference2pruning2sparsity2transformers2efficiency1vision-transformer1vision-transformers1
7 stories, newest first · one card per story
Stories tagged #dinov3
Your Transformer Is Secretly Elastic
A retraining-free method makes pretrained transformers elastic, pruning smoothly to 60% sparsity with small accuracy loss.
Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate
RAESR restores images in a frozen DINOv3-L latent space, leading reported super-resolution quality and speed.
Image Classifiers are Efficient Self-Supervised Video Representation Learners
VideoMSN turns pretrained image ViTs into efficient video learners, cutting pretraining by up to 160x.
TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining
TT-VidT pairs a DINOv3 spatial ViT with a temporal layer, leading motion benchmarks at lower FLOPs.
FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders
FuseReg trains decoders on random encoder-layer subsets, narrowing the reconstruction-generation gap in RAEs.
Cross-modal learning for SAR target recognition using optical vision foundation models
Frozen DINOv3 optical prototypes supervise SAR target recognition without EO/SAR pairs, improving classification on the heavily imbalanced UNICORNv2 dataset.