Vision-Language Models (VLMs) such as CLIP are now foundational to multimodal systems, yet their robustness to spurious correlations remains poorly understood at scale. We present the first large-scale empirical study of 194 publicly available VLMs, including 16 model families, covering a wide range of model sizes, 24 training datasets, and three evaluation benchmarks, namely ImageNet (overall performance), CelebA (typical single-attribute bias), and UrbanCars (complex multi-attribute biases).
arXiv:2606. 04409v1 Announce Type: cross Abstract: Modern deep neural networks usually have large parameter scales and nonlinear hierarchical structures, and they have achieved strong performance in computer vision.
By Luoyidi Zhou
arXiv:2602.01718v2 Announce Type: replace
Abstract: Predicting generalization from quantities available before target-test evaluation remains a central challenge in deep learning. The systematic benc...
By Sora Nakai, Youssef Fadhloun, Kacem Mathlouthi, Kotaro Yoshida, Ganesh Talluri, Ioannis Mitliagkas, Hiroki Naganuma
arXiv:2607. 00371v1 Announce Type: cross Abstract: Visual AutoRegressive modeling (VAR) has pioneered a coarse-to-fine multi-scale autoregressive generative paradigm, demonstrating strong capabilities in image generation.
By Nuoyan Zhou, Zhijun Tu, Lei Yu, Kun Cheng, Jie Hu, Nannan Wang, Xinghao Chen
arXiv:2608.23182v1 Announce Type: cross
Abstract: We present a comparative study of label-free metrics for assessing the quality of representations in deep neural networks to understand their reliabi...
By Daniel Richards Arputharaj, Daniel J\"onsson, Gabriel Eilertsen
arXiv:2505. 03201v4 Announce Type: replace-cross Abstract: Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential.
By Kien Tran Duc Tuan, Tam Nguyen Trong, Son Nguyen Hoang, Khoat Than, Anh Nguyen Duc
arXiv:2601.17723v3 Announce Type: replace
Abstract: Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). However, no systematic emp...
By Tayyab Nasir, Daochang Liu, Ajmal Mian
arXiv:2609.06581v1 Announce Type: cross
Abstract: Small-object detection remains challenging because limited pixels cause information loss and suppress the scale knowledge encoded in pretrained detec...
By Zhaoning Shi, Bo Ma
arXiv:2609.26512v1 Announce Type: new
Abstract: Convolutional neural networks (CNNs) and vision transformers are both used to model the human visual system, but whether the two architectures diverge...
By Shashank Baghel, Kshitij Dwivedi, Dinesh Singh, Sanjeev Nara
arXiv:2609.23561v1 Announce Type: new
Abstract: Deploying efficient neural networks is essential in resource-constrained environments, yet compact models often sacrifice interpretability - a critical...
By Aleks Czufarow, Ihor Babin
The paper reviews 50 image augmentation and generation techniques, categorizing them into ten groups, and conducts a large‑scale empirical study to assess their effectiveness as test generators for embedding‑based image retrieval systems. Using Amazon Titan and OpenCLIP embeddings, the authors evaluate the techniques across four dimensions—embedding‑space similarity, embedding uncertainty, semantic realism, and retrieval failure rate—on CIFAR‑10, ImageNet‑1K, and an industrial dataset. Results show that weather simulation and SaSPA yield the highest uncertainty and failure rates while maintaining realistic visuals, whereas GAN‑based methods produce low realism due to synthetic artifacts.
By Yehan De Silva, Anirudh Sridhar, Armin Lotfy, Nafiseh Kahani, Yvan Labiche, Ziyu Wang, Frank Ouyang, Clare Carty, Azalia Shamsaei
The paper introduces the Capability-Driven Multimodal Scaling Law, a cross-family framework that predicts vision-language model (VLM) benchmark accuracy from a low-dimensional textual capability score extracted via PCA. By training over 150 VLMs on 34 large language models across seven families, the authors demonstrate that the law accurately extrapolates transfer rates from 8B to 72B‑parameter backbones, predicts full training trajectories, and generalizes to unseen model families. The study also reveals actionable insights, such as certain textual benchmarks negatively correlating with multimodal performance and base LLMs outperforming instruction-tuned counterparts as VLM backbones due to higher absorption rates.
By Ziran Li, Qiang Wang, Zhengyu Chen, Shanglin Lei, Borun Chen, Jingang Wang, Xunliang Cai