English
Related papers

Related papers: SimpleOCR: Rendering Visualized Questions to Teach…

200 papers

Despite strong performance on vision-language tasks, Multimodal Large Language Models (MLLMs) struggle with mathematical problem-solving, with both open-source and state-of-the-art models falling short of human performance on visual-math…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 William Rudman , Michal Golovanevsky , Amir Bar , Vedant Palit , Yann LeCun , Carsten Eickhoff , Ritambhara Singh

Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We identify a core deployment misalignment in generative OCR. Autoregressive decoding favors…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Weile Gong , Yiping Zuo , Zijian Lu , Xin He , Weibei Fan , Lianyong Qi , Shi Jin

Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able to synthesize vision-centric problems spanning diverse levels…

Computer Vision and Pattern Recognition · Computer Science 2026-02-18 David Acuna , Chao-Han Huck Yang , Yuntian Deng , Jaehun Jung , Ximing Lu , Prithviraj Ammanabrolu , Hyunwoo Kim , Yuan-Hong Liao , Yejin Choi

Visual Question Answering (VQA) research seeks to create AI systems to answer natural language questions in images, yet VQA methods often yield overly simplistic and short answers. This paper aims to advance the field by introducing Visual…

Computer Vision and Pattern Recognition · Computer Science 2024-11-13 Jialu Li , Manish Kumar Thota , Ruslan Gokhman , Radek Holik , Youshan Zhang

Large Vision-Language Models (LVLMs) have shown remarkable progress in various multimodal tasks, yet they often struggle with complex visual reasoning that requires multi-step inference. To address this limitation, we propose MF-SQ-LLaVA, a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Liu Jing , Amirul Rahman

Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Qing'an Liu , Juntong Feng , Yuhao Wang , Xinzhe Han , Yujie Cheng , Yue Zhu , Haiwen Diao , Yunzhi Zhuge , Huchuan Lu

State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality primarily via projecting the vision tokens from the encoder to language-like tokens, which are directly fed to the Large Language Model (LLM)…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Sivan Doveh , Shaked Perek , M. Jehanzeb Mirza , Wei Lin , Amit Alfassy , Assaf Arbelle , Shimon Ullman , Leonid Karlinsky

Despite the rapid progress of multimodal large language models (MLLMs), they have largely overlooked the importance of visual processing. In a simple yet revealing experiment, we interestingly find that language-only models, when provided…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Yuting Li , Lai Wei , Kaipeng Zheng , Jingyuan Huang , Guilin Li , Bo Wang , Linghe Kong , Lichao Sun , Weiran Huang

Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on…

Machine Learning · Computer Science 2025-03-27 Yuncheng Guo , Xiaodong Gu

With growing interest in recent years, medical visual question answering (Med-VQA) has rapidly evolved, with multimodal large language models (MLLMs) emerging as an alternative to classical model architectures. Specifically, their ability…

Computer Vision and Pattern Recognition · Computer Science 2024-08-07 Sergio Tascon-Morales , Pablo Márquez-Neila , Raphael Sznitman

With the continuous expansion of Large Language Models (LLMs) and advances in reinforcement learning, LLMs have demonstrated exceptional reasoning capabilities, enabling them to address a wide range of complex problems. Inspired by these…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Hongrui Jia , Chaoya Jiang , Shikun Zhang , Wei Ye

Emerging multimodal large language models (MLLMs) exhibit great potential for chart question answering (CQA). Recent efforts primarily focus on scaling up training datasets (i.e., charts, data tables, and question-answer (QA) pairs) through…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Xingchen Zeng , Haichuan Lin , Yilin Ye , Wei Zeng

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

Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investigate this, we introduce ViLP, a benchmark featuring…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Tiange Luo , Ang Cao , Gunhee Lee , Justin Johnson , Honglak Lee

This paper proposes to improve visual question answering (VQA) with structured representations of both scene contents and questions. A key challenge in VQA is to require joint reasoning over the visual and text domains. The predominant…

Computer Vision and Pattern Recognition · Computer Science 2017-03-31 Damien Teney , Lingqiao Liu , Anton van den Hengel

An increasing number of vision-language tasks can be handled with little to no training, i.e., in a zero and few-shot manner, by marrying large language models (LLMs) to vision encoders, resulting in large vision-language models (LVLMs).…

Computation and Language · Computer Science 2024-04-03 Archiki Prasad , Elias Stengel-Eskin , Mohit Bansal

Language provides a natural interface to specify and evaluate performance on visual tasks. To realize this possibility, vision language models (VLMs) must successfully integrate visual and linguistic information. Our work compares VLMs to a…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Stephanie Fu , Tyler Bonnen , Devin Guillory , Trevor Darrell

Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Ioanna Ntinou , Alexandros Xenos , Yassine Ouali , Adrian Bulat , Georgios Tzimiropoulos

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…

Computer Vision and Pattern Recognition · Computer Science 2024-05-31 Siddharth Karamcheti , Suraj Nair , Ashwin Balakrishna , Percy Liang , Thomas Kollar , Dorsa Sadigh

In recent years, notable advancements have been made in the domain of visual document understanding, with the prevailing architecture comprising a cascade of vision and language models. The text component can either be extracted explicitly…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Ofir Abramovich , Niv Nayman , Sharon Fogel , Inbal Lavi , Ron Litman , Shahar Tsiper , Royee Tichauer , Srikar Appalaraju , Shai Mazor , R. Manmatha