arXiv Computer Vision
TileShare: Training-Free Acceleration of Overlapping Tiled ViT Decoding
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Oct 1
PrePARE: Pre-AA Token Pruning for Frozen Multi-View Geometry Transformers
arXiv:2605.08371v2 Announce Type: replace Abstract: Multi-view geometry transformers are feed-forward 3D foundation models that jointly predict depth maps, point maps, and camera poses for N images i...
arXiv Computer Vision
2d ago
Triage: Skip, Skim, or Refine Attention Tiles in Video Diffusion Transformers
arXiv:2610.35706v1 Announce Type: cross Abstract: Attention over tens of thousands of visual tokens dominates the inference of video diffusion transformers (DiTs). Existing methods reduce this cost t...
Hugging Face Trending Papers
Aug 18
DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance
DistillPath-KS16 is a 22‑million‑parameter ViT‑S/16 pathology encoder distilled from larger teachers ranging from 86 M to 1.1 B parameters. By training only on the teachers’ final class and patch tokens across 6,000 public slides, it avoids costly pretraining heads and large tile corpora, yet surpasses the kaiko baseline on EVA, HEST, and PLISM benchmarks. The strongest variant, DistillPath-KS16‑Virchow2, achieves a mean EVA score of 0.795—just 0.015 points below the top model—while being 29× smaller and 25× faster.
arXiv AI
1d ago
Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs
arXiv:2610.36671v1 Announce Type: cross Abstract: Diffusion vision-language models (DVLMs) process their entire input at every denoising step. Since visual tokens make up 89-97% of this input on the...
arXiv AI
Oct 7
Later Is Better: Token Reduction for ViTs Under Distribution Shift
arXiv:2610.07758v1 Announce Type: cross Abstract: Training-free token reduction accelerates vision transformers by removing redundant tokens across layers, recovering most of the original accuracy at...
arXiv AI
Aug 28
LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.