中文
相关论文

相关论文: Seeing without Looking: Do Vision-Language Benchma…

200 篇论文

Pre-trained vision language models still fall short of human visual cognition. In an effort to improve visual cognition and align models with human behavior, we introduce visual stimuli and human judgments on visual cognition tasks,…

Despite significant advances in vision-language models (VLMs), most existing work follows an English-centric design process, limiting their effectiveness in multilingual settings. In this work, we provide a comprehensive empirical study…

Despite tremendous advancements, current state-of-the-art Vision-Language Models (VLMs) are still far from perfect. They tend to hallucinate and may generate biased responses. In such circumstances, having a way to assess the reliability of…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Qian Yang , Weixiang Yan , Aishwarya Agrawal

Vision capabilities in vision large language models (VLLMs) have consistently lagged behind their linguistic capabilities. In particular, numerous benchmark studies have demonstrated that VLLMs struggle when fine-grained visual information…

计算机视觉与模式识别 · 计算机科学 2026-02-09 Darryl Hannan , John Cooper , Dylan White , Yijing Watkins

Large Vision Language Models (LVLMs) have demonstrated remarkable abilities in understanding and reasoning about both visual and textual information. However, existing evaluation methods for LVLMs, primarily based on benchmarks like Visual…

计算机视觉与模式识别 · 计算机科学 2025-03-05 Xinyu Wang , Bohan Zhuang , Qi Wu

Object hallucination in Large Vision-Language Models (LVLMs) significantly impedes their real-world applicability. As the primary component for accurately interpreting visual information, the choice of visual encoder is pivotal. We…

计算机视觉与模式识别 · 计算机科学 2025-09-18 Weihang Wang , Xinhao Li , Ziyue Wang , Yan Pang , Jielei Zhang , Peiyi Li , Qiang Zhang , Longwen Gao

Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to uncover salient…

Recent advances in Vision-Language Models (VLMs) have improved performance in multi-modal learning, raising the question of whether these models truly understand the content they process. Crucially, can VLMs detect when a reasoning process…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Yang Shi , Yifeng Xie , Minzhe Guo , Liangsi Lu , Mingxuan Huang , Jingchao Wang , Zhihong Zhu , Boyan Xu , Zhiqi Huang

Recent multimodal large language models (MLLMs) achieve strong performance on visual reasoning benchmarks, yet it remains unclear to what extent such performance reflects reasoning directly grounded in visual evidence. We introduce…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Longteng Guo , Yifan Wang , Pengkang Huo , Tailai Chen , Yuze Wu , Jing Liu , Xinxin Zhu

Image classification is one of the most fundamental capabilities of machine vision intelligence. In this work, we revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Yuhui Zhang , Alyssa Unell , Xiaohan Wang , Dhruba Ghosh , Yuchang Su , Ludwig Schmidt , Serena Yeung-Levy

Vision-language models (VLMs) excel at extracting and reasoning about information from images. Yet, their capacity to leverage internal knowledge about specific entities remains underexplored. This work investigates the disparity in model…

计算与语言 · 计算机科学 2026-01-06 Ido Cohen , Daniela Gottesman , Mor Geva , Raja Giryes

Given the higher information load processed by large vision-language models (LVLMs) compared to single-modal LLMs, detecting LVLM hallucinations requires more human and time expense, and thus rise a wider safety concerns. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Ruiyang Zhang , Hu Zhang , Zhedong Zheng

Recent breakthroughs in vision-language models (VLMs) start a new page in the vision community. The VLMs provide stronger and more generalizable feature embeddings compared to those from ImageNet-pretrained models, thanks to the training on…

计算机视觉与模式识别 · 计算机科学 2024-04-05 Jieneng Chen , Qihang Yu , Xiaohui Shen , Alan Yuille , Liang-Chieh Chen

Vision-Language Models (VLMs) have demonstrated remarkable performance across a variety of real-world tasks. However, existing VLMs typically process visual information by serializing images, a method that diverges significantly from the…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Yueyan Li , Chenggong Zhao , Zeyuan Zang , Caixia Yuan , Xiaojie Wang

Humans perform visual perception at multiple levels, including low-level object recognition and high-level semantic interpretation such as behavior understanding. Subtle differences in low-level details can lead to substantial changes in…

计算机视觉与模式识别 · 计算机科学 2024-10-08 Guanzhen Li , Yuxi Xie , Min-Yen Kan

A reliable driving assistant should provide consistent responses based on temporally grounded reasoning derived from observed information. In this work, we investigate whether Vision-Language Models (VLMs), when applied as driving…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Chun-Peng Chang , Chen-Yu Wang , Holger Caesar , Alain Pagani

Vision-Language Models like GPT-4, LLaVA, and CogVLM have surged in popularity recently due to their impressive performance in several vision-language tasks. Current evaluation methods, however, overlook an essential component: uncertainty,…

计算机视觉与模式识别 · 计算机科学 2024-02-27 Vasily Kostumov , Bulat Nutfullin , Oleg Pilipenko , Eugene Ilyushin

Can warping tokens, rather than pixels, help multimodal large language models (MLLMs) understand how a scene appears from a nearby viewpoint? While MLLMs perform well on visual reasoning, they remain fragile to viewpoint changes, as…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Phillip Y. Lee , Chanho Park , Mingue Park , Seungwoo Yoo , Juil Koo , Minhyuk Sung

Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and…

计算机视觉与模式识别 · 计算机科学 2024-05-31 Siddharth Karamcheti , Suraj Nair , Ashwin Balakrishna , Percy Liang , Thomas Kollar , Dorsa Sadigh

Vision and language model (VLM) decoders are currently the best-performing architectures on multimodal tasks. Next to answers, they are able to produce natural language explanations, either in post-hoc or CoT settings. However, it is not…

计算与语言 · 计算机科学 2025-05-05 Letitia Parcalabescu , Anette Frank
‹ 上一页 1 8 9 10 下一页 ›