arXiv:2606. 08132v1 Announce Type: cross Abstract: Vision Transformers operate on fixed patch grids, which can introduce phase-dependent instability for dense prediction: changing the patch partition can change the token evidence available to a pixel, especially near boundaries.
arXiv:2607. 28589v1 Announce Type: cross Abstract: Post-training quantization (PTQ) has emerged as an effective solution for deploying Vision Transformers (ViTs) on resource-constrained devices.
Visual Geometry Grounded Transformer (VGGT) recovers dense 3D scene structure from multi-view images in one forward pass, but quadratic cross-frame attention limits its scalability. Existing training-free accelerators reduce computation uniformly along one axis, missing layer heterogeneity.
arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.
arXiv:2608. 16658v1 Announce Type: cross Abstract: Cross-view Video Geo-localization (CVG) aims to localize ground-view videos by retrieving their corresponding geo-tagged aerial images.
arXiv:2608. 10660v1 Announce Type: cross Abstract: Continuous and reliable localization is essential for autonomous driving.
arXiv:2608. 09325v1 Announce Type: new Abstract: Newly triggered landslides rarely carry immediate annotations, so cross-domain transferability determines the value of landslide mapping for emergency response and regional risk assessment.
arXiv:2608. 15349v1 Announce Type: cross Abstract: To accelerate single image super-resolution (SISR) networks on large images (2K-8K), many recent approaches decompose an image into small patches and dynamically determine an execution path according to its difficulty (referred to as a dynamic network).
SPARC is a few‑shot calibration technique for vision‑based industrial anomaly detectors that corrects deployment‑time nuisances by projecting patch features onto a per‑cell subspace, requiring only up to eight verified‑normal images and no gradient updates. It operates between the encoder and detector, using a closed‑form, spatially indexed estimate based on the encoder’s native patch grid. Across seven detectors on shift‑prone benchmarks, SPARC boosts pooled Image AUROC by 13.8 pp and AU‑PRO₀.₃ by 3.5 pp, while showing modest changes on benchmarks without engineered shift.
arXiv:2607. 00174v1 Announce Type: cross Abstract: We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and input preprocessing pipeline.
arXiv:2603. 12433v3 Announce Type: replace-cross Abstract: Model stitching, connecting early layers of one model (source) to later layers of another (target) via a light stitch layer, has served as a probe of representational compatibility.
Fewer visual tokens do not guarantee lower end-to-end latency. We evaluate break-even with a reproducible protocol that accounts for decision overhead, shared work, and the operators each policy can avoid.
arXiv:2602. 06883v3 Announce Type: replace Abstract: The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness.