中文
相关论文

相关论文: MLLMs Know Where to Look: Training-free Perception…

200 篇论文

Multimodal Large Language Models (MLLMs) have recently shown remarkable perceptual capability in answering visual questions, however, little is known about the limits of their perception. In particular, while prior works have provided…

计算机视觉与模式识别 · 计算机科学 2024-02-13 Jiarui Zhang , Jinyi Hu , Mahyar Khayatkhoei , Filip Ilievski , Maosong Sun

Multimodal Large Language Models (MLLMs) have displayed remarkable performance in multi-modal tasks, particularly in visual comprehension. However, we reveal that MLLMs often generate incorrect answers even when they understand the visual…

计算机视觉与模式识别 · 计算机科学 2025-03-20 Yexin Liu , Zhengyang Liang , Yueze Wang , Xianfeng Wu , Feilong Tang , Muyang He , Jian Li , Zheng Liu , Harry Yang , Sernam Lim , Bo Zhao

Multimodal Large Language Models (MLLMs) have recently achieved promising zero-shot accuracy on visual question answering (VQA) -- a fundamental task affecting various downstream applications and domains. Given the great potential for the…

计算机视觉与模式识别 · 计算机科学 2024-02-13 Jiarui Zhang , Mahyar Khayatkhoei , Prateek Chhikara , Filip Ilievski

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. Vision detection models excel at recognizing…

计算机视觉与模式识别 · 计算机科学 2024-12-20 Qirui Jiao , Daoyuan Chen , Yilun Huang , Yaliang Li , Ying Shen

Multimodal Large Language Models (MLLMs) often struggle with fine-grained perception, such as identifying small objects in high-resolution images or detecting key moments in long videos. Existing methods typically rely on complex,…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Sanghwan Kim , Rui Xiao , Stephan Alaniz , Yongqin Xian , Zeynep Akata

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

Recent advancements have enhanced the capability of Multimodal Large Language Models (MLLMs) to comprehend multi-image information. However, existing benchmarks primarily evaluate answer correctness, overlooking whether models genuinely…

计算机视觉与模式识别 · 计算机科学 2025-05-26 Pengfei Wang , Guohai Xu , Weinong Wang , Junjie Yang , Jie Lou , Yunhua Xue

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in multimodal reasoning. However, they often excessively rely on textual information during the later stages of inference, neglecting the crucial integration of…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Shuo Yang , Yuwei Niu , Yuyang Liu , Yang Ye , Bin Lin , Li Yuan

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on…

计算机视觉与模式识别 · 计算机科学 2025-11-12 Jing Bi , Junjia Guo , Yunlong Tang , Lianggong Bruce Wen , Zhang Liu , Chenliang Xu

In this work, we propose a training-free method to inject visual prompts into Multimodal Large Language Models (MLLMs) through test-time optimization of a learnable latent variable. We observe that attention, as the core module of MLLMs,…

计算机视觉与模式识别 · 计算机科学 2025-01-08 Mingrui Wu , Xinyue Cai , Jiayi Ji , Jiale Li , Oucheng Huang , Gen Luo , Hao Fei , Guannan Jiang , Xiaoshuai Sun , Rongrong Ji

Multimodal large language models (MLLMs) are changing how Blind and Low Vision (BLV) people access visual information. Unlike traditional visual interpretation tools that only provide descriptions, MLLM-enabled applications offer…

人机交互 · 计算机科学 2026-02-20 Ricardo E. Gonzalez Penuela , Crescentia Jung , Sharon Y Lin , Ruiying Hu , Shiri Azenkot

Large Vision-Language Models (LVLMs) have shown promising performance in vision-language understanding and reasoning tasks. However, their visual understanding behaviors remain underexplored. A fundamental question arises: to what extent do…

计算机视觉与模式识别 · 计算机科学 2025-03-19 Xiaoying Xing , Chia-Wen Kuo , Li Fuxin , Yulei Niu , Fan Chen , Ming Li , Ying Wu , Longyin Wen , Sijie Zhu

In-context learning (ICL) enables Large Language Models (LLMs) to learn tasks from demonstration examples without parameter updates. Although it has been extensively studied in LLMs, its effectiveness in Vision-Language Models (VLMs)…

机器学习 · 计算机科学 2025-10-29 Gabriel O. dos Santos , Esther Colombini , Sandra Avila

With the rapid advancement of Multimodal Large Language Models (MLLMs), a variety of benchmarks have been introduced to evaluate their capabilities. While most evaluations have focused on complex tasks such as scientific comprehension and…

计算机视觉与模式识别 · 计算机科学 2024-12-24 Huan Liu , Lingyu Xiao , Jiangjiang Liu , Xiaofan Li , Ze Feng , Sen Yang , Jingdong Wang

Recent advances in multimodal large language models (MLLMs) have demonstrated strong capabilities in understanding general visual content. However, these general-domain MLLMs perform poorly in face perception tasks, often producing…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Jingzhi Li , Changjiang Luo , Ruoyu Chen , Hua Zhang , Wenqi Ren , Jianhou Gan , Xiaochun Cao

Transformer-based language models, though not explicitly trained to mimic brain recordings, have demonstrated surprising alignment with brain activity. Progress in these models-through increased size, instruction-tuning, and…

Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Wei-Yao Wang , Zhao Wang , Helen Suzuki , Yoshiyuki Kobayashi

When humans describe a visual scene, they do not process the entire image uniformly; instead, they selectively fixate on regions relevant to their intended description. In contrast, current multimodal large language models (MLLMs) attend to…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Junha Song , Byeongho Heo , Geonmo Gu , Jaegul Choo , Dongyoon Han , Sangdoo Yun

This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the prediction of a specialized vision model can improve recognition…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Guoyuan An , JaeYoon Kim , SungEui Yoon

The development of Large Vision-Language Models (LVLMs) is striving to catch up with the success of Large Language Models (LLMs), yet it faces more challenges to be resolved. Very recent works enable LVLMs to localize object-level visual…

计算机视觉与模式识别 · 计算机科学 2024-03-20 Zhipeng Huang , Zhizheng Zhang , Zheng-Jun Zha , Yan Lu , Baining Guo
‹ 上一页 1 2 3 10 下一页 ›