Imagen de Portada

Exploring Implicit Visual Misunderstandings in Multimodal Large Language Models through Attention Analysis

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Pengfei, Xu, Guohai, Wang, Weinong, Yang, Junjie, Lou, Jie, Xue, Yunhua
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning
por: Ma, Yiwei, et al.
Publicado: (2025)

Visual Implicit Autoregressive Modeling
por: Jiang, Pengfei, et al.
Publicado: (2026)

VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack
por: Zhao, Shiji, et al.
Publicado: (2025)

PIDNet: Progressive Implicit Decouple Network for Multimodal Action Quality Assessment
por: Li, Qiqi, et al.
Publicado: (2026)

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
por: Dong, Yuhao, et al.
Publicado: (2024)

Visual Attention Drifts,but Anchors Hold:Mitigating Hallucination in Multimodal Large Language Models via Cross-Layer Visual Anchors
por: Yang, Chengxu, et al.
Publicado: (2026)

Debiasing Multimodal Large Language Models via Penalization of Language Priors
por: Zhang, YiFan, et al.
Publicado: (2024)

IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
por: Yang, Jiabing, et al.
Publicado: (2025)

Attention-driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models without Fine-Tuning
por: Xu, Hai-Ming, et al.
Publicado: (2024)

Adversarial Robustness for Visual Grounding of Multimodal Large Language Models
por: Gao, Kuofeng, et al.
Publicado: (2024)

Survey of Adversarial Robustness in Multimodal Large Language Models
por: Jiang, Chengze, et al.
Publicado: (2025)

DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Models
por: Zhou, Yue, et al.
Publicado: (2026)

Implicit and Explicit Language Guidance for Diffusion-based Visual Perception
por: Wang, Hefeng, et al.
Publicado: (2024)

Parameter-Efficient Fine-Tuning Medical Multimodal Large Language Models for Medical Visual Grounding
por: He, Jinlong, et al.
Publicado: (2024)

Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge
por: Wang, Yuxuan, et al.
Publicado: (2024)

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
por: Guo, Jiayi, et al.
Publicado: (2025)

MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models
por: Chen, Jian, et al.
Publicado: (2025)

GroundVTS: Visual Token Sampling in Multimodal Large Language Models for Video Temporal Grounding
por: Fan, Rong, et al.
Publicado: (2026)

Large Language Models for Multimodal Deformable Image Registration
por: Ma, Mingrui, et al.
Publicado: (2024)

Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach
por: Bi, Jing, et al.
Publicado: (2024)

Personal Visual Context Learning in Large Multimodal Models
por: Xue, Zihui, et al.
Publicado: (2026)

EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models
por: Wang, Yahong, et al.
Publicado: (2026)

Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation
por: Zhu, Xingyu, et al.
Publicado: (2026)

LEAML: Label-Efficient Adaptation to Out-of-Distribution Visual Tasks for Multimodal Large Language Models
por: Lin, Ci-Siang, et al.
Publicado: (2025)

DeepEyesV2: Toward Agentic Multimodal Model
por: Hong, Jack, et al.
Publicado: (2025)

Introducing Visual Perception Token into Multimodal Large Language Model
por: Yu, Runpeng, et al.
Publicado: (2025)

Q Cache: Visual Attention is Valuable in Less than Half of Decode Layers for Multimodal Large Language Model
por: Zhuang, Jiedong, et al.
Publicado: (2026)

DUALVISION: RGB-Infrared Multimodal Large Language Models for Robust Visual Reasoning
por: Majeedi, Abrar, et al.
Publicado: (2026)

Exploring the Transferability of Visual Prompting for Multimodal Large Language Models
por: Zhang, Yichi, et al.
Publicado: (2024)

Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning
por: Chen, Jiahua, et al.
Publicado: (2026)

SedarEval: Automated Evaluation using Self-Adaptive Rubrics
por: Fan, Zhiyuan, et al.
Publicado: (2025)

Improving Visual Storytelling with Multimodal Large Language Models
por: Lin, Xiaochuan, et al.
Publicado: (2024)

Visual Representation Alignment for Multimodal Large Language Models
por: Yoon, Heeji, et al.
Publicado: (2025)

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models
por: Tang, Jianting, et al.
Publicado: (2025)

Demystifying the Visual Quality Paradox in Multimodal Large Language Models
por: Xing, Shuo, et al.
Publicado: (2025)

CoVFT: Context-aware Visual Fine-tuning for Multimodal Large Language Models
por: Zhou, Nan, et al.
Publicado: (2026)

Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
por: Liu, Haogeng, et al.
Publicado: (2024)

LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models
por: Liu, Juntao, et al.
Publicado: (2025)

ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model
por: Sun, Yiming, et al.
Publicado: (2024)

PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models
por: Xu, Zhaopan, et al.
Publicado: (2025)