中文
相关论文

相关论文: Understanding Language Prior of LVLMs by Contrasti…

200 篇论文

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

计算机视觉与模式识别 · 计算机科学 2025-07-03 Aarti Ghatkesar , Ganesh Venkatesh

Large vision-language models (LVLMs) achieve impressive performance, yet their internal decision-making processes remain opaque, making it difficult to determine if the success stems from true multimodal fusion or from reliance on unimodal…

机器学习 · 计算机科学 2026-04-01 Lixin Xiu , Xufang Luo , Hideki Nakayama

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language understanding, yet how they internally integrate visual and textual information remains poorly understood. To bridge this gap, we perform a…

计算机视觉与模式识别 · 计算机科学 2026-01-14 Shezheng Song , Shasha Li , Jie Yu

Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Current methods either disrupt the model's inherent structure or…

计算机视觉与模式识别 · 计算机科学 2025-06-23 Tongtian Yue , Longteng Guo , Yepeng Tang , Zijia Zhao , Xinxin Zhu , Hua Huang , Jing Liu

In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information. The dominant connector-based paradigm projects visual…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Xinpeng Dong , Min Zhang , Kairong Han , Xu Tan , Fei Wu , Kun Kuang

The Large Vision-Language Model (LVLM) has enhanced the performance of various downstream tasks in visual-language understanding. Most existing approaches encode images and videos into separate feature spaces, which are then fed as inputs…

计算机视觉与模式识别 · 计算机科学 2024-10-02 Bin Lin , Yang Ye , Bin Zhu , Jiaxi Cui , Munan Ning , Peng Jin , Li Yuan

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…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Tiange Luo , Ang Cao , Gunhee Lee , Justin Johnson , Honglak Lee

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared…

Large Language Models (LLMs), despite being trained on text alone, surprisingly develop rich visual priors. These priors allow latent visual capabilities to be unlocked for vision tasks with a relatively small amount of multimodal data, and…

机器学习 · 计算机科学 2025-10-01 Junlin Han , Shengbang Tong , David Fan , Yufan Ren , Koustuv Sinha , Philip Torr , Filippos Kokkinos

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…

人工智能 · 计算机科学 2025-08-14 Zixian Guo , Ming Liu , Qilong Wang , Zhilong Ji , Jinfeng Bai , Lei Zhang , Wangmeng Zuo

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,…

计算与语言 · 计算机科学 2026-05-28 Jinzhou Wu , Zhengwu Ma , Jixing Li , Baoping Tang , Zitong Lu

Large Vision-Language Models (LVLMs) have shown impressive performance in various tasks. However, LVLMs suffer from hallucination, which hinders their adoption in the real world. Existing studies emphasized that the strong language priors…

计算机视觉与模式识别 · 计算机科学 2025-02-19 Zongyu Wu , Yuwei Niu , Hongcheng Gao , Minhua Lin , Zhiwei Zhang , Zhifang Zhang , Qi Shi , Yilong Wang , Sike Fu , Junjie Xu , Junjie Ao , Enyan Dai , Lei Feng , Xiang Zhang , Suhang Wang

Multimodal large language models (MLLMs) have enabled a wide range of advanced vision-language applications, including fine-grained object recognition and contextual understanding. When querying specific regions or objects in an image,…

The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution. Nevertheless, these LLMs exhibit a notable limitation, as they are primarily adept at processing textual information. To address this…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Akash Ghosh , Arkadeep Acharya , Sriparna Saha , Vinija Jain , Aman Chadha

Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Clement Neo , Luke Ong , Philip Torr , Mor Geva , David Krueger , Fazl Barez

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…

计算机视觉与模式识别 · 计算机科学 2024-04-26 Shengbang Tong , Zhuang Liu , Yuexiang Zhai , Yi Ma , Yann LeCun , Saining Xie

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…

计算机视觉与模式识别 · 计算机科学 2025-10-13 Haoran Chen , Junyan Lin , Xinghao Chen , Yue Fan , Jianfeng Dong , Xin Jin , Hui Su , Jinlan Fu , Xiaoyu Shen

Large Language Model-based Vision-Language Models (LLM-based VLMs) have demonstrated impressive results in various vision-language understanding tasks. However, how well these VLMs can see image detail beyond the semantic level remains…

计算机视觉与模式识别 · 计算机科学 2024-08-08 Chenhui Gou , Abdulwahab Felemban , Faizan Farooq Khan , Deyao Zhu , Jianfei Cai , Hamid Rezatofighi , Mohamed Elhoseiny

Vision Large Language Models (VLLMs) usually take input as a concatenation of image token embeddings and text token embeddings and conduct causal modeling. However, their internal behaviors remain underexplored, raising the question of…

计算与语言 · 计算机科学 2025-05-16 Houjing Wei , Yuting Shi , Naoya Inoue

Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in comprehending complex visual content. However, the mechanisms underlying how VLMs process visual information remain largely unexplored. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2024-11-27 Omri Kaduri , Shai Bagon , Tali Dekel
‹ 上一页 1 2 3 10 下一页 ›