English
Related papers

Related papers: Focusing Where Vision Matters: Selective Training …

200 papers

Engagement recognition in video datasets, unlike traditional image classification tasks, is particularly challenged by subjective labels and noise limiting model performance. To overcome the challenges of subjective and noisy engagement…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Alexander Vedernikov , Puneet Kumar , Haoyu Chen , Tapio Seppänen , Xiaobai Li

Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge not only in natural language tasks, but also in some vision-language tasks such as open-domain knowledge-based visual question…

Computation and Language · Computer Science 2024-06-11 Ziyue Wang , Chi Chen , Peng Li , Yang Liu

Pre-trained LLMs that are further trained with image data perform well on vision-language tasks. While adding images during a second training phase effectively unlocks this capability, it is unclear how much of a gain or loss this two-step…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Sedrick Keh , Jean Mercat , Samir Yitzhak Gadre , Kushal Arora , Igor Vasiljevic , Benjamin Burchfiel , Shuran Song , Russ Tedrake , Thomas Kollar , Ludwig Schmidt , Achal Dave

Large Vision-Language Models (LVLMs) have demonstrated outstanding performance across various multimodal tasks. However, they suffer from a problem known as language prior, where responses are generated based solely on textual patterns…

Artificial Intelligence · Computer Science 2025-02-11 Kang-il Lee , Minbeom Kim , Seunghyun Yoon , Minsung Kim , Dongryeol Lee , Hyukhun Koh , Kyomin Jung

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Artificial Intelligence · Computer Science 2025-08-14 Zixian Guo , Ming Liu , Qilong Wang , Zhilong Ji , Jinfeng Bai , Lei Zhang , Wangmeng Zuo

Continual learning enables pre-trained generative vision-language models (VLMs) to incorporate knowledge from new tasks without retraining data from previous ones. Recent methods update a visual projector to translate visual information for…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Hyundong Jin , Hyung Jin Chang , Eunwoo Kim

It is widely agreed that open-vocabulary-based approaches outperform classical closed-set training solutions for recognizing unseen objects in images for semantic segmentation. Existing open-vocabulary approaches leverage vision-language…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Huadong Tang , Youpeng Zhao , Yan Huang , Min Xu , Jun Wang , Qiang Wu

Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs) to integrate visual and textual information. This paper presents a comprehensive analysis of…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Shweta Mahajan , Hoang Le , Hyojin Park , Farzad Farhadzadeh , Munawar Hayat , Fatih Porikli

Large Vision Language Models (LVLMs) have recently emerged as powerful architectures capable of understanding and reasoning over both visual and textual information. These models typically rely on two key components: a Vision Transformer…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Jiayun Luo , Wan-Cyuan Fan , Lyuyang Wang , Xiangteng He , Tanzila Rahman , Purang Abolmaesumi , Leonid Sigal

Large Vision-Language Models (VLMs) are increasingly being regarded as foundation models that can be instructed to solve diverse tasks by prompting, without task-specific training. We examine the seemingly obvious question: how to…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Niccolo Avogaro , Thomas Frick , Mattia Rigotti , Andrea Bartezzaghi , Filip Janicki , Cristiano Malossi , Konrad Schindler , Roy Assaf

Vision-language models (VLMs) achieve remarkable success in single-image tasks. However, real-world scenarios often involve intricate multi-image inputs, leading to a notable performance decline as models struggle to disentangle critical…

Computer Vision and Pattern Recognition · Computer Science 2025-04-30 Juntian Zhang , Chuanqi cheng , Yuhan Liu , Wei Liu , Jian Luan , Rui Yan

Instruction tuning of large vision-language models (LVLMs) increasingly depends on massive multimodal corpora, yet these datasets contain samples with substantial redundancy, low visual dependency, and highly imbalanced coverage of…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Shristi Das Biswas , Kaushik Roy

Vision and Language Models (VLMs), such as CLIP, have enabled visual recognition of a potentially unlimited set of categories described by text prompts. However, for the best visual recognition performance, these models still require tuning…

Computer Vision and Pattern Recognition · Computer Science 2023-09-14 M. Jehanzeb Mirza , Leonid Karlinsky , Wei Lin , Horst Possegger , Rogerio Feris , Horst Bischof

Pre-trained large vision-language models (VLMs) like CLIP have revolutionized visual representation learning using natural language as supervisions, and demonstrated promising generalization ability. In this work, we propose ViP, a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Xiao Fang , Yi Lin , Dong Zhang , Kwang-Ting Cheng , Hao Chen

In high-stakes domains, small task-specific vision models are crucial due to their low computational requirements and the availability of numerous methods to explain their results. However, these explanations often reveal that the models do…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Alexander Koebler , Lukas Kuhn , Ingo Thon , Florian Buettner

In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Yan Fang , Mengcheng Lan , Zilong Huang , Weixian Lei , Yunqing Zhao , Yujie Zhong , Yingchen Yu , Qi She , Yao Zhao , Yunchao Wei

In standard large vision-language models (LVLMs) pre-training, the model typically maximizes the joint probability of the caption conditioned on the image via next-token prediction (NTP); however, since only a small subset of caption tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-05-15 Yangyi Chen , Hao Peng , Tong Zhang , Heng Ji

Instruction tuning is a crucial supervised training phase in Large Language Models (LLMs), aiming to enhance the LLM's ability to generalize instruction execution and adapt to user preferences. With the increasing integration of multi-modal…

Multimedia · Computer Science 2023-11-28 Chen Li , Yixiao Ge , Dian Li , Ying Shan

Despite progress in Large Vision-Language Models (LVLMs), their capacity for visual reasoning is often limited by the binding problem: the failure to reliably associate perceptual features with their correct visual referents. This…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Amirmohammad Izadi , Mohammad Ali Banayeeanzade , Fatemeh Askari , Ali Rahimiakbar , Mohammad Mahdi Vahedi , Hosein Hasani , Mahdieh Soleymani Baghshah

Large language models (LLMs) have become increasingly useful computational models of human language processing, but it remains unclear whether vision-language learning makes text representations more human-like during natural reading. Here,…

Computation and Language · Computer Science 2026-05-28 Jinzhou Wu , Zhengwu Ma , Jixing Li , Baoping Tang , Zitong Lu