10 citations · 10 across the 3 of their papers we have counts for
3 papers
cs.CV2025
CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones
Wenyi Gong, Mieszko Lis
Many modern ViT backbones adopt spatial architectural designs, such as window attention, decomposed relative positional embeddings in SAM, and RoPE in DINOv3. Such architectures im…
cs.NE2020
Procrustes: a Dataflow and Accelerator for Sparse Deep Neural Network Training
Dingqing Yang, Amin Ghasemazar, Xiaowei Ren +3
The success of DNN pruning has led to the development of energy-efficient inference accelerators that support pruned models with sparse weight and activation tensors. Because the m…
cs.LG2018★ 10 cited
Full deep neural network training on a pruned weight budget
Maximilian Golub, Guy Lemieux, Mieszko Lis
We introduce a DNN training technique that learns only a fraction of the full parameter set without incurring an accuracy penalty. To do this, our algorithm constrains the total nu…