English
Related papers

Related papers: Towards Perceiving Small Visual Details in Zero-sh…

200 papers

Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…

Computation and Language · Computer Science 2023-11-29 Utsav Garg , Erhan Bas

Multimodal Large Language Models (MLLMs) have displayed remarkable performance in multi-modal tasks, particularly in visual comprehension. However, we reveal that MLLMs often generate incorrect answers even when they understand the visual…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Yexin Liu , Zhengyang Liang , Yueze Wang , Xianfeng Wu , Feilong Tang , Muyang He , Jian Li , Zheng Liu , Harry Yang , Sernam Lim , Bo Zhao

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Bangzheng Li , Fei Wang , Wenxuan Zhou , Nan Xu , Ben Zhou , Sheng Zhang , Hoifung Poon , Muhao Chen

In question-answering scenarios, humans can assess whether the available information is sufficient and seek additional information if necessary, rather than providing a forced answer. In contrast, Vision Language Models (VLMs) typically…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Li Liu , Diji Yang , Sijia Zhong , Kalyana Suma Sree Tholeti , Lei Ding , Yi Zhang , Leilani H. Gilpin

Despite advancements in Multimodal Large Language Models (MLLMs), their proficiency in fine-grained video motion understanding remains critically limited. They often lack inter-frame differencing and tend to average or ignore subtle visual…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Yipeng Du , Tiehan Fan , Kepan Nan , Rui Xie , Penghao Zhou , Xiang Li , Jian Yang , Zhenheng Yang , Ying Tai

Recently, Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in visual understanding and reasoning across various vision-language tasks. However, we found that MLLMs cannot process effectively from…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Bangyan Li , Wenxuan Huang , Zhenkun Gao , Yeqiang Wang , Yunhang Shen , Jingzhong Lin , Ling You , Yuxiang Shen , Shaohui Lin , Wanli Ouyang , Yuling Sun

This paper presents novel benchmarks for evaluating vision-language models (VLMs) in zero-shot recognition, focusing on granularity and specificity. Although VLMs excel in tasks like image captioning, they face challenges in open-world…

Computer Vision and Pattern Recognition · Computer Science 2024-06-19 Zhenlin Xu , Yi Zhu , Tiffany Deng , Abhay Mittal , Yanbei Chen , Manchen Wang , Paolo Favaro , Joseph Tighe , Davide Modolo

Visual question answering (VQA) has traditionally been treated as a single-step task where each question receives the same amount of effort, unlike natural human question-answering strategies. We explore a question decomposition strategy…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Zaid Khan , Vijay Kumar BG , Samuel Schulter , Manmohan Chandraker , Yun Fu

Large Multimodal Models (LMMs) often rely on in-context learning (ICL) to perform new visual question answering (VQA) tasks with minimal supervision. However, ICL performance, especially in smaller LMMs, does not always improve…

Artificial Intelligence · Computer Science 2026-03-03 Akash Gupta , Amos Storkey , Mirella Lapata

Pretrained vision-language models (VLMs), e.g., CLIP, demonstrate impressive zero-shot capabilities on downstream tasks. Prior research highlights the crucial role of visual augmentation techniques, like random cropping, in alignment with…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Lincan Cai , Jingxuan Kang , Shuang Li , Wenxuan Ma , Binhui Xie , Zhida Qin , Jian Liang

Multimodal Large Language Models (MLLMs) show strong performance in Visual Question Answering (VQA) but remain limited in fine-grained reasoning due to low-resolution inputs and noisy attention aggregation. We propose \textbf{Head Aware…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Junfei Xie , Peng Pan , Xulong Zhang

Large-scale pre-trained models (PTMs) show great zero-shot capabilities. In this paper, we study how to leverage them for zero-shot visual question answering (VQA). Our approach is motivated by a few observations. First, VQA questions often…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Rui Cao , Jing Jiang

Aligning the recent large language models (LLMs) with computer vision models leads to large vision-language models (LVLMs), which have paved the way for zero-shot image reasoning tasks. However, LVLMs are usually trained on short high-level…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Kaiwen Yang , Tao Shen , Xinmei Tian , Xiubo Geng , Chongyang Tao , Dacheng Tao , Tianyi Zhou

Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that Multi-modal Large Language Models (MLLMs)…

Computer Vision and Pattern Recognition · Computer Science 2024-03-14 Yanqing Liu , Kai Wang , Wenqi Shao , Ping Luo , Yu Qiao , Mike Zheng Shou , Kaipeng Zhang , Yang You

Large Vision-Language Models (LVLMs) have achieved strong performance on vision-language tasks, particularly Visual Question Answering (VQA). While prior work has explored unimodal biases in VQA, the problem of selection bias in…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Md. Atabuzzaman , Ali Asgarov , Chris Thomas

Recent advances in Image Quality Assessment (IQA) have leveraged Multi-modal Large Language Models (MLLMs) to generate descriptive explanations. However, despite their strong visual perception modules, these models often fail to reliably…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Yuan Li , Zitang Sun , Yen-Ju Chen , Shin'ya Nishida

Vision-Language multimodal Models (VLMs) offer the possibility for zero-shot classification in astronomy: i.e. classification via natural language prompts, with no training. We investigate two models, GPT-4o and LLaVA-NeXT, for zero-shot…

Instrumentation and Methods for Astrophysics · Physics 2024-06-26 Dimitrios Tanoglidis , Bhuvnesh Jain

Text-rich VQA, namely Visual Question Answering based on text recognition in the images, is a cross-modal task that requires both image comprehension and text recognition. In this work, we focus on investigating the advantages and…

Computer Vision and Pattern Recognition · Computer Science 2023-11-14 Xuejing Liu , Wei Tang , Xinzhe Ni , Jinghui Lu , Rui Zhao , Zechao Li , Fei Tan

Multimodal large language models (MLLMs) still struggle with complex reasoning tasks in Visual Question Answering (VQA). While current methods have advanced by incorporating visual prompts, our study uncovers critical limitations: these…

Computation and Language · Computer Science 2025-06-03 Songtao Jiang , Chenyi Zhou , Yan Zhang , Yeying Jin , Zuozhu Liu

The linguistic capabilities of Multimodal Large Language Models (MLLMs) are critical for their effective application across diverse tasks. This study aims to evaluate the performance of MLLMs on the VALSE benchmark, focusing on the efficacy…

Computation and Language · Computer Science 2024-07-18 Mustafa Dogan , Ilker Kesen , Iacer Calixto , Aykut Erdem , Erkut Erdem