HiLRP introduces a unified attribution framework for Vision Transformers (ViTs) that addresses the challenges posed by diverse architectural designs. By decomposing ViT operations into four basic types—linear maps, bilinear mixing, normalization/gating, and reindexing—HiLRP applies conservation‑satisfying relevance rules, enabling reliable explanations across a wide range of backbones. The method outperforms 14 existing attribution techniques on 10 architectures, maintaining conservation and improving localization accuracy (0.97 Pointing) compared to competitors.
By Sathiyamohan Nishankar, Pubudu Sanjeewani, Asanka Perera, Selvarajah Thuseethan
arXiv:2505. 15441v5 Announce Type: replace-cross Abstract: Natural images exhibit strong geometric regularities: local structures, such as edges, corners, and textures, appear in many orientations and mirror configurations.
By David Nordstr\"om, Johan Edstedt, Fredrik Kahl, Georg B\"okman
arXiv:2609.23733v1 Announce Type: new
Abstract: Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-v...
By Abteen Arab, Guile Wu, Chengjie Huang, Dongfeng Bai
arXiv:2610.01785v1 Announce Type: cross
Abstract: Processing long videos with Vision-Language Models (VLMs) is bottlenecked by the quadratic cost of visual tokens, making long-form inference prohibit...
By Gueter Josmy Faure, Hao Ping Wang, Min-Hung Chen, Winston H. Hsu
arXiv:2607. 02097v1 Announce Type: cross Abstract: Large kernel depthwise convolutions achieve strong performance but suffer from significant degradation as kernel size grows due to irregular memory access from gather-based computation; while Large Kernel Acceleration (LKA) helps on small feature maps, it becomes counterproductive on large feature maps, even slower than non-accelerated implementations.
By Wan Song, Wei Zhou, Rui Wang, Jun Yu, Toru Kurihara, Jiajia Xu, Shu Zhan
FreeFlow is a hierarchical transformer for optical flow estimation that eliminates traditional flow-specific inductive biases such as correlation volumes, feature warping, and iterative refinement. It relies on a single feed-forward encoder–decoder architecture that integrates window attention for local processing, shifted-window attention for cross-window communication, and global attention at reduced resolution. This design allows the model to scale naturally with capacity, achieving state-of-the-art performance on Sintel, KITTI-2015, and Spring benchmarks while remaining memory efficient at 1080p inference.
By Vladislav Bargatin, Alexander Yakovenko, Khaled Abud, Dmitriy Vatolin
arXiv:2606. 14757v1 Announce Type: cross Abstract: Though Vision Transformers (ViTs) have become the dominant backbone in many computer vision tasks, due to permutation equivariance, their attention mechanism lacks explicit spatial inductive biases.
By Leyla Naz Candogan, Arshia Afzal, Pol Puigdemont, Volkan Cevher
arXiv:2505.16157v3 Announce Type: replace
Abstract: Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Tran...
By Yuang Ai
arXiv:2607. 00774v1 Announce Type: cross Abstract: Recent recursive Transformer studies have primarily reused shared parameters across computation steps to construct compact, parameter-efficient models.
By Sang In Lee, Jihun Park
arXiv:2606. 27449v1 Announce Type: new Abstract: Multi-head attention conventionally partitions the hidden dimension equally across all heads at every layer, enforcing an identical representational subspace dimension (dh = dmodel/h) throughout the models depth.
By Shubham Aggarwal
arXiv:2607. 03784v1 Announce Type: cross Abstract: While prior studies have successfully compressed vision Transformers (ViTs) through various pruning techniques, most have concentrated on width pruning to achieve significant reductions in model size.
By Zhenfeng Su, Kang Zhao, Han Bao, Tao Yuan, Zhongzhe Hu, Xianzhi Yu, Wenxuan Wang
TT-VidT is a video pretraining method that decouples the temporal axis by combining a per‑frame ViT-B/16 spatial encoder with a compact Temporal Transfer Layer trained via Diff Compression. The authors conduct a systematic 24‑configuration study to isolate architecture, objective, and decoder effects, showing that the full TT-VidT design yields the strongest motion‑sensitive representations. In downstream fine‑tuning, TT‑VidT outperforms state‑of‑the‑art baselines on Jester, Something‑Something V2, ARID, and Diving48 while using significantly fewer encoder FLOPs.
By Shih-Ying Yeh, Daniel Z. Kaplan, Xuehai Wang, Fu-En Yang, Min-Hung Chen, Shang-Hong Lai