English
Related papers

Related papers: Visual Generation Unlocks Human-Like Reasoning thr…

200 papers

Vision-Language Models (VLMs) have shown remarkable progress in visual understanding in recent years. Yet, they still lag behind human capabilities in specific visual tasks such as counting or relational reasoning. To understand the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Zihan Weng , Lucas Gomez , Taylor Whittington Webb , Pouya Bashivan

Chain-of-Thought reasoning has driven large language models to extend from thinking with text to thinking with images and videos. However, different modalities still have clear limitations: static images struggle to represent temporal…

Artificial Intelligence · Computer Science 2026-02-04 Andong Chen , Wenxin Zhu , Qiuyu Ding , Yuchen Song , Muyun Yang , Tiejun Zhao

The human brain is naturally equipped to comprehend and interpret visual information rapidly. When confronted with complex problems or concepts, we use flowcharts, sketches, and diagrams to aid our thought process. Leveraging this inherent…

Computer Vision and Pattern Recognition · Computer Science 2023-11-17 Fanxu Meng , Haotong Yang , Yiding Wang , Muhan Zhang

Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Jingqi Zhou , Sheng Wang , Jingwei Dong , Kai Liu , Lei Li , Jiahui Gao , Jiyue Jiang , Lingpeng Kong , Chuan Wu

Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning. However, existing CoT-based T2I methods largely…

Artificial Intelligence · Computer Science 2026-03-10 Haodong Li , Chunmei Qing , Huanyu Zhang , Dongzhi Jiang , Yihang Zou , Hongbo Peng , Dingming Li , Yuhong Dai , ZePeng Lin , Juanxi Tian , Yi Zhou , Siqi Dai , Jingwei Wu

Image editing with natural language has gained significant popularity, yet existing methods struggle with intricate object intersections and fine-grained spatial relationships due to the lack of an explicit reasoning process. While…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Zhentao Zou , Zhengrong Yue , Kunpeng Du , Binlei Bao , Hanting Li , Haizhen Xie , Guozheng Xu , Yue Zhou , Yali Wang , Jie Hu , Xue Jiang , Xinghao Chen

Generalization in Visual Question Answering (VQA) requires models to answer questions about images with contexts beyond the training distribution. Existing attempts primarily refine unimodal aspects, overlooking enhancements in multimodal…

Artificial Intelligence · Computer Science 2023-10-10 Trang Nguyen , Naoaki Okazaki

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Binbin Ji , Siddharth Agrawal , Qiance Tang , Yvonne Wu

Large language models equipped with retrieval-augmented generation (RAG) represent a burgeoning field aimed at enhancing answering capabilities by leveraging external knowledge bases. Although the application of RAG with language-only…

Computer Vision and Pattern Recognition · Computer Science 2024-06-03 Cheng Tan , Jingxuan Wei , Linzhuang Sun , Zhangyang Gao , Siyuan Li , Bihui Yu , Ruifeng Guo , Stan Z. Li

Medical vision-language models (VLMs) achieve strong performance in diagnostic reporting and image-text alignment, yet their underlying reasoning mechanisms remain fundamentally correlational, exhibiting reliance on superficial statistical…

Machine Learning · Computer Science 2026-01-27 Weiqin Yang , Haowen Xue , Qingyi Peng , Hexuan Hu , Qian Huang , Tingbo Zhang

Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Qian Liang , Yujia Wu , Kuncheng Li , Jiwei Wei , Shiyuan He , Jinyu Guo , Ning Xie

Humor, as both a creative human activity and a social binding mechanism, has long posed a major challenge for AI generation. Although producing humor requires complex cognitive reasoning and social understanding, theories of humor suggest…

Computation and Language · Computer Science 2026-03-25 Jiajun Zhang , Shijia Luo , Ruikang Zhang , Qi Su

Recent advancements in unified vision-language models (VLMs), which integrate both visual understanding and generation capabilities, have attracted significant attention. The underlying hypothesis is that a unified architecture with mixed…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Jihai Zhang , Tianle Li , Linjie Li , Zhengyuan Yang , Yu Cheng

While large multi-modal models (LMMs) have exhibited impressive capabilities across diverse tasks, their effectiveness in handling complex tasks has been limited by the prevailing single-step reasoning paradigm. To this end, this paper…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Zejun Li , Ruipu Luo , Jiwen Zhang , Minghui Qiu , Xuanjing Huang , Zhongyu Wei

Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can parse natural queries about the visual content and generate human-like outputs. In this work, we explore the ability of these models to…

Computation and Language · Computer Science 2024-03-21 Yangyi Chen , Karan Sikka , Michael Cogswell , Heng Ji , Ajay Divakaran

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

Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to recognize and reason about the same concept despite variations…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Zahra Babaiee , Peyman M. Kiasari , Daniela Rus , Radu Grosu

Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Wanyue Zhang , Wenxiang Wu , Wang Xu , Jiaxin Luo , Helu Zhi , Yibin Huang , Shuo Ren , Zitao Liu , Jiajun Zhang

Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear. Existing benchmarks lack a systematic exploration of the specific tasks where…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Zimo Wen , Boxiu Li , Wanbo Zhang , Junxiang Lei , Xiaoyu Chen , Yijia Fan , Qi Zhang , Yujiang Wang , Lili Qiu , Bo Li , Ziwei Liu , Caihua Shan , Yifan Yang , Yifei Shen

Multimodal reasoning aims to enhance the capabilities of MLLMs by incorporating intermediate reasoning steps before reaching the final answer. It has evolved from text-only reasoning to the integration of visual information, enabling the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Chao Chen , Zhixin Ma , Yongqi Li , Yupeng Hu , Yinwei Wei , Wenjie Li , Liqiang Nie