English
Related papers

Related papers: How Vision Becomes Language: A Layer-wise Informat…

200 papers

Effective multimodal reasoning depends on the alignment of visual and linguistic representations, yet the mechanisms by which vision-language models (VLMs) achieve this alignment remain poorly understood. Following the LiMBeR framework, we…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Constantin Venhoff , Ashkan Khakzar , Sonia Joseph , Philip Torr , Neel Nanda

We consider the problem of Vision-and-Language Navigation (VLN). The majority of current methods for VLN are trained end-to-end using either unstructured memory such as LSTM, or using cross-modal attention over the egocentric observations…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Georgios Georgakis , Karl Schmeckpeper , Karan Wanchoo , Soham Dan , Eleni Miltsakaki , Dan Roth , Kostas Daniilidis

Reasoning has emerged as a pivotal capability in Large Language Models (LLMs). Through Reinforcement Learning (RL), typically Group Relative Policy Optimization (GRPO), these models are able to solve complex tasks such as mathematics and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Xinyu Tian , Shu Zou , Zhaoyuan Yang , Mengqi He , Fabian Waschkowski , Lukas Wesemann , Peter Tu , Jing Zhang

Self-supervised vision-and-language pretraining (VLP) aims to learn transferable multi-modal representations from large-scale image-text data and to achieve strong performances on a broad scope of vision-language tasks after finetuning.…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Yongfei Liu , Chenfei Wu , Shao-yen Tseng , Vasudev Lal , Xuming He , Nan Duan

Vision-language models (VLMs) have demonstrated impressive performance by effectively integrating visual and textual information to solve complex tasks. However, it is not clear how these models reason over the visual and textual data…

Artificial Intelligence · Computer Science 2025-04-15 Pouya Pezeshkpour , Moin Aminnaseri , Estevam Hruschka

The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs)…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Yana Wei , Liang Zhao , Jianjian Sun , Kangheng Lin , Jisheng Yin , Jingcheng Hu , Yinmin Zhang , En Yu , Haoran Lv , Zejia Weng , Jia Wang , Chunrui Han , Yuang Peng , Qi Han , Zheng Ge , Xiangyu Zhang , Daxin Jiang , Vishal M. Patel

Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on localized patch-based embeddings that are insufficient to…

Computation and Language · Computer Science 2026-04-10 Mengdan Zhu , Senhao Cheng , Liang Zhao

Visual Question Answering systems target answering open-ended textual questions given input images. They are a testbed for learning high-level reasoning with a primary use in HCI, for instance assistance for the visually impaired. Recent…

Computer Vision and Pattern Recognition · Computer Science 2021-07-21 Theo Jaunet , Corentin Kervadec , Romain Vuillemot , Grigory Antipov , Moez Baccouche , Christian Wolf

Vision model have gained increasing attention due to their simplicity and efficiency in Scene Text Recognition (STR) task. However, due to lacking the perception of linguistic knowledge and information, recent vision models suffer from two…

Computer Vision and Pattern Recognition · Computer Science 2023-05-11 Boqiang Zhang , Hongtao Xie , Yuxin Wang , Jianjun Xu , Yongdong Zhang

Multi-modal document pre-trained models have proven to be very effective in a variety of visually-rich document understanding (VrDU) tasks. Though existing document pre-trained models have achieved excellent performance on standard…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Chuwei Luo , Guozhi Tang , Qi Zheng , Cong Yao , Lianwen Jin , Chenliang Li , Yang Xue , Luo Si

Multimodal large language models (MLLMs) that think with images can interactively use tools to reason about visual inputs, but current approaches often rely on a narrow set of tools with limited real-world necessity and scalability. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Zirun Guo , Minjie Hong , Feng Zhang , Kai Jia , Tao Jin

We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text. Powered by the iterative latent cross-attention of Perceiver, our framework scales with…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Zineng Tang , Jaemin Cho , Jie Lei , Mohit Bansal

While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding, they frequently falter in fine-grained perception tasks that require identifying tiny objects or discerning subtle…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Jilong Zhu , Yang Feng

Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the image has been counterfactually modified. We present a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Xuesong Wang , Harry Wang

Vision-language models (VLMs) have demonstrated strong reasoning abilities in literal multimodal tasks such as visual mathematics and science question answering. However, figurative language, such as sarcasm, humor, and metaphor, remains a…

Computation and Language · Computer Science 2026-01-27 Seyyed Saeid Cheshmi , Hahnemann Ortiz , James Mooney , Dongyeop Kang

Large vision-language models (VLMs) often benefit from intermediate visual cues, either injected via external tools or generated as latent visual tokens during reasoning, but these mechanisms still overlook fine-grained visual evidence…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Shuoshuo Zhang , Yizhen Zhang , Jingjing Fu , Lei Song , Jiang Bian , Yujiu Yang , Rui Wang

Multimodal large language models (MLLMs) typically extract visual features from the final layers of a pretrained Vision Transformer (ViT). This widespread deep-layer bias, however, is largely driven by empirical convention rather than…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Haoran Chen , Junyan Lin , Xinghao Chen , Yue Fan , Jianfeng Dong , Xin Jin , Hui Su , Jinlan Fu , Xiaoyu Shen

Vision--language models (VLMs) often process visual inputs through a pretrained vision encoder, followed by a projection into the language model's embedding space via a connector component. While crucial for modality fusion, the potential…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Wenyan Li , Raphael Tang , Chengzu Li , Caiqi Zhang , Ivan Vulić , Anders Søgaard

Is vision good enough for language? Recent advancements in multimodal models primarily stem from the powerful reasoning abilities of large language models (LLMs). However, the visual component typically depends only on the instance-level…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Shengbang Tong , Zhuang Liu , Yuexiang Zhai , Yi Ma , Yann LeCun , Saining Xie

Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Xuchen Li , Xuzhao Li , Jiahui Gao , Renjie Pi , Shiyu Hu , Wentao Zhang