2026· International Conference on Language Resources and Evaluation· pp. 9368-9385· 0 citations· 58 references
Computer Science
TL;DR
By reducing the difficulty of discriminability, the ablation studies elucidate that vision encoders cannot distinguish visual details well, given generally similar but partially different images.
Generative vision-language models (VLMs) such as Qwen-VL and LLaVA achieve strong zero-shot performance on tasks overlapping with their pretraining distribution, yet fail on specialized domains where the required discriminative features were never learned, a regime we term distant out-of-distribution (OOD). Standard ad...
Hung-Jen Chen, Yuek F. Ho, Ting-Yao Huang et al.· European Conference on Compu...· 0 citations
Results show that pretrained convolutional representations, when integrated through learned adaptation and fusion, can improve the visual understanding of existing VLMs without replacing their original visual encoders.
This paper presents the first comprehensive survey of VLM applications in low-level vision, proposing a unified taxonomy that organizes existing literature into two complementary paradigms, and identifies critical open challenges, including semantic-pixel misalignment and computational efficiency.
Feng-Yang Xiao, May May Liqeliqe Mar. Liqe Mar., Mariusz Dec et al.· 0 citations
Few-shot classification (FSC) aims to emulate the human ability to rapidly learn new concepts from a handful of examples. Large Vision-Language Models (LVLMs), with their rich prior knowledge and powerful visio-linguistic understanding capabilities, are emerging as a highly promising paradigm for FSC. This paper invest...
Chuan-Yi Zhang, Fan Liu, Yi Xu et al.· IEEE Transactions on Image P...· 0 citations
Evaluating vision encoders requires metrics that reliably predict their downstream performance in multimodal large language models (MLLMs). Although recent studies have shown that cross-modal metrics can better capture such performance, unimodal metrics remain the dominant choice in practice. In this work, we revisit c...
Yilin Yang, Jun Tang, Keng-Yi Wang et al.· 0 citations
This work constructs a signal by force-decoding a fixed set of candidate answers and develops a framework that manipulates the image and question text separately, making the boundary searchable for any behaviour formulated as a choice between candidate answers.
R. Kaiser· Proceedings of the 41st IEEE...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.