Imagen de Portada

Rethinking Causal Mask Attention for Vision-Language Inference

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pei, Xiaohuan, Huang, Tao, Ma, YanXiang, Xu, Chang
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Cross-Self KV Cache Pruning for Efficient Vision-Language Inference
por: Pei, Xiaohuan, et al.
Publicado: (2024)

EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba
por: Pei, Xiaohuan, et al.
Publicado: (2024)

LocalMamba: Visual State Space Model with Windowed Selective Scan
por: Huang, Tao, et al.
Publicado: (2024)

Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models
por: Shi, Yuheng, et al.
Publicado: (2026)

SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining
por: Song, Chull Hwan, et al.
Publicado: (2024)

Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration
por: Zhu, Younan, et al.
Publicado: (2025)

Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos
por: Fei, Jiajun, et al.
Publicado: (2024)

HyDRA: Hierarchical and Dynamic Rank Adaptation for Mobile Vision Language Model
por: Xi, Yuanhao, et al.
Publicado: (2025)

ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models
por: Yang, Cheng, et al.
Publicado: (2026)

EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients
por: Wu, Meihan, et al.
Publicado: (2024)

Rethinking Token Reduction for Large Vision-Language Models
por: Wang, Yi, et al.
Publicado: (2026)

Refer to Any Segmentation Mask Group With Vision-Language Prompts
por: Cao, Shengcao, et al.
Publicado: (2025)

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models
por: Arif, Kazi Hasan Ibn, et al.
Publicado: (2024)

MaskAnyNet: Rethinking Masked Image Regions as Valuable Information in Supervised Learning
por: Hong, Jingshan, et al.
Publicado: (2025)

Multimodal Causal Reasoning Benchmark: Challenging Vision Large Language Models to Discern Causal Links Across Modalities
por: Li, Zhiyuan, et al.
Publicado: (2024)

Seeing Through the Mask: Rethinking Adversarial Examples for CAPTCHAs
por: Jabary, Yahya, et al.
Publicado: (2024)

Vision-and-Language Navigation via Causal Learning
por: Wang, Liuyi, et al.
Publicado: (2024)

AEMIM: Adversarial Examples Meet Masked Image Modeling
por: Xiang, Wenzhao, et al.
Publicado: (2024)

Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models
por: Wang, Zhiqiang, et al.
Publicado: (2026)

LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel
por: Feng, Zhe, et al.
Publicado: (2026)

Self-Attention with State-Object Weighted Combination for Compositional Zero Shot Learning
por: Chang, Cheng-Hong, et al.
Publicado: (2025)

Enhancing Medical Large Vision-Language Models via Alignment Distillation
por: Chang, Aofei, et al.
Publicado: (2025)

PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language Models
por: Yokomizo, Hisayuki, et al.
Publicado: (2026)

Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models
por: Zhao, Yunhan, et al.
Publicado: (2025)

Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models
por: Zhang, Naifu, et al.
Publicado: (2025)

Towards Robust Vision Transformer via Masked Adaptive Ensemble
por: Lin, Fudong, et al.
Publicado: (2024)

CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion
por: Böhle, Moritz, et al.
Publicado: (2025)

Where Reliability Lives in Vision-Language Models: A Mechanistic Study of Attention, Hidden States, and Causal Circuits
por: Mann, Logan, et al.
Publicado: (2026)

Causal-SAM-LLM: Large Language Models as Causal Reasoners for Robust Medical Segmentation
por: Tang, Tao, et al.
Publicado: (2025)

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models
por: Dong, Xinpeng, et al.
Publicado: (2026)

Large Vision-Language Models Get Lost in Attention
por: Xi, Gongli, et al.
Publicado: (2026)

Attention Prompting on Image for Large Vision-Language Models
por: Yu, Runpeng, et al.
Publicado: (2024)

Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
por: Yu, Lu, et al.
Publicado: (2024)

MedHEval: Benchmarking Hallucinations and Mitigation Strategies in Medical Large Vision-Language Models
por: Chang, Aofei, et al.
Publicado: (2025)

Collaborative Edge-to-Server Inference for Vision-Language Models
por: Song, Soochang, et al.
Publicado: (2025)

Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation
por: Kim, Subin, et al.
Publicado: (2025)

InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models
por: Tao, Hongyuan, et al.
Publicado: (2025)

Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering
por: Liu, Shuliang, et al.
Publicado: (2026)

MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
por: Li, Chenxi, et al.
Publicado: (2025)

DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
por: Zhang, Yudong, et al.
Publicado: (2024)