Cats and humans differ in ocular anatomy. Most notably, Felis Catus (domestic cats) have vertically elongated pupils linked to ambush predation; yet, how such specializations manifest in downstream visual representations remains incompletely understood. We present a unified, frozen-encoder benchmark that quantifies feline-human cross-species representational alignment in the wild, across convolutional networks, supervised Vision Transformers, windowed transformers, and self-supervised ViTs (DINO), using layer-wise Centered Kernel Alignment (linear and RBF) and Representational Similarity Analysis, with additional distributional and stability tests reported in the paper. Across models, DINO ViT-B/16 attains the most substantial alignment (mean CKA-RBF $\approx0.814$, mean CKA-linear $\approx0.745$, mean RSA $\approx0.698$), peaking at early blocks, indicating that token-level self-supervision induces early-stage features that bridge species-specific statistics. Supervised ViTs are competitive on CKA yet show weaker geometric correspondence than DINO (e.g., ViT-B/16 RSA $\approx0.53$ at block8; ViT-L/16 $\approx0.47$ at block14), revealing depth-dependent divergences between similarity and representational geometry. CNNs remain strong baselines but below plain ViTs on alignment, and windowed transformers underperform plain ViTs, implicating architectural inductive biases in cross-species alignment. Results indicate that self-supervision coupled with ViT inductive biases yields representational geometries that more closely align feline and human visual systems than widely used CNNs and windowed Transformers, providing testable neuroscientific hypotheses about where and how cross-species visual computations converge. We release our code and dataset for reference and reproducibility.
Self-Distilled Vision Transformer for Domain Generalization
Mohamed Bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Oxford Brookes University（牛津布鲁克斯大学）；Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）
From Colors to Classes: Emergence of Concepts in Vision Transformers
Technical University of Denmark（丹麦技术大学）；UiT The Arctic University of Norway（挪威北极大学）；University of Copenhagen（哥本哈根大学）；Norwegian Computing Center（挪威计算中心）
Does Explainability Transfer? A Controlled Benchmark of Attribution Methods on Vision Transformers and CNNs
Faculty of Computing, Sabaragamuwa University of Sri Lanka（斯里兰卡萨巴拉加穆瓦大学计算机学院）；Faculty of Engineering, University of Moratuwa（莫拉图瓦大学工程学院）；School of Computing Technologies, RMIT University（RMIT大学计算技术学院）；School of Engineering & Digital Technologies, University of Southern Queensland（南昆士兰大学工程与数字技术学院）；School of Engineering & Technologies, UNSW（新南威尔士大学工程与技术学院）；Faculty of Science and Technology, Charles Darwin University（查尔斯达尔文大学科学技术学院）
Experts Weights Averaging: A New General Training Scheme for Vision Transformers
School of Information Science and Technology, Fudan University（复旦大学信息科学与技术学院）；Shanghai AI Lab（上海人工智能实验室）；Jiangxi University of Finance and Economics（江西财经大学）
GLACIA: Instance-Aware Positional Reasoning for Glacial Lake Segmentation via Multimodal Large Language Model
Portsmouth AI and Data Science Centre (PAIDS), School of Computing, University of Portsmouth（普森大学计算学院）；Center for Sustainability and the Global Environment (SAGE), University of Wisconsin–Madison（威斯康星大学麦迪逊分校可持续性与全球环境中心）
Towards Transferable Adversarial Attacks on Vision Transformers
Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University（复旦大学计算机科学技术学院上海市智能信息处理重点实验室）；Shanghai Collaborative Innovation Center on Intelligent Visual Computing（上海智能视觉计算协同创新中心）；Department of Computer Science, University of Maryland（马里兰大学计算机科学系）
The University of Sydney（悉尼大学）；SenseTime Research（商汤科技研究院）；Tsinghua University（清华大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；University of Science and Technology of China（中国科学技术大学）；The Chinese University of Hong Kong（香港中文大学）
Vision Transformers（ViTs）继承了NLP的成功，但它们的结构还没有得到充分的研究和优化视觉任务。最简单的解决方案之一是通过CNN中广泛使用的神经结构搜索（NAS）直接搜索最优解。然而，我们根据经验发现，这种直接的适应会遇到灾难性的失败，并且对于训练优秀者来说非常不稳定。在本文中，我们认为，由于ViT主要在令牌嵌入上操作，几乎没有归纳偏差，因此不同架构的通道不平衡会恶化权重共享假设，从而导致训练不稳定。因此，我们开发了一种新的循环权重共享机制，用于ViT的令牌嵌入，这使得每个通道可以更均匀地贡献给所有候选架构。此外，我们还提出了身份转换，以减轻多对一的问题，在superperformer和利用弱增强和正则化技术更稳定的训练经验。基于这些，我们提出的方法，ViTAS，已经取得了显着的优势，在DeiT和Twins为基础的ViTs。例如，仅使用$1.4$ G FLOP预算，我们搜索的架构具有比基线DeiT更高的$3.3\%$ ImageNet- $1$ k精度。使用$3.0$ G FLOPs，我们的结果在ImageNet- $1$ k上实现了$82.0\%$的准确性，在COCO $2017$上实现了$45.9\%$ mAP，这是$2.4\%$优于其他ViT。
Texture Representations in Deep Vision Models: Comparing CNNs, Vision Transformers, and Human Perception
Department of Neuroscience International School for Advanced Studies (SISSA) Trieste Italy（神经科学系国际先进研究学院（SISSA）特里埃斯特意大利）；Department of Language and Translation Sciences Pompeu Fabra University Barcelona Spain（语言与翻译科学系庞培法布拉大学巴塞罗那西班牙）；ICREA Barcelona Spain（ICREA巴塞罗那西班牙）；Department of Data Science International School for Advanced Studies (SISSA) Trieste Italy（数据科学系国际先进研究学院（SISSA）特里埃斯特意大利）
Evaluating Graphical Perception Capabilities of Vision Transformers
Viscom Group, Institute of Media Informatics, Ulm University（Viscom集团，媒体信息学研究所，乌尔姆大学）；ViRVIG Group, Universitat Politècnica de Catalunya - BarcelonaTech（ViRVIG集团，巴塞罗那技术大学-加泰罗尼亚理工大学）；Ulm University（乌尔姆大学）
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs
Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；MEGVII Technology（旷视科技）；Aberystwyth University（阿伯里斯特威斯大学）
VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings
São Carlos Institute of Physics, University of São Paulo（圣保罗大学圣卡洛斯物理研究所）；KTH Royal Institute of Technology（瑞典皇家理工学院）；São Paulo State University（圣保罗州立大学）
Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs
Shanghai Jiao Tong University, China（上海交通大学）；Southeast University, China（东南大学）；Mohamed bin Zayed University of Artificial Intelligence, UAE（穆罕默德·本·扎耶德人工智能大学）；National University of Singapore, Singapore（新加坡国立大学）
