Imagen de Portada

Egocentric Bias in Vision-Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Maijunxian, Li, Yijiang, Wang, Bingyang, Zhao, Tianwei, Ji, Ran, Gao, Qingying, Liu, Emmy, Deng, Hokin, Luo, Dezhi
Formato:	Preprint
Publicado:	2026
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

Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues
por: Zhang, Zory, et al.
Publicado: (2025)

Core Knowledge Deficits in Multi-Modal Language Models
por: Li, Yijiang, et al.
Publicado: (2024)

Probing Perceptual Constancy in Large Vision-Language Models
por: Sun, Haoran, et al.
Publicado: (2025)

Vision Language Models Cannot Reason About Physical Transformation
por: Luo, Dezhi, et al.
Publicado: (2026)

Probing Mechanical Reasoning in Large Vision Language Models
por: Sun, Haoran, et al.
Publicado: (2024)

Video Models Start to Solve Chess, Maze, Sudoku, Mental Rotation, and Raven' Matrices
por: Deng, Hokin
Publicado: (2025)

Vision Language Models See What You Want but not What You See
por: Gao, Qingying, et al.
Publicado: (2024)

Vision Language Models Know Law of Conservation without Understanding More-or-Less
por: Luo, Dezhi, et al.
Publicado: (2024)

Increasing Computation Resolves Conflicts in Vision Language Models
por: Wang, Bingyang, et al.
Publicado: (2025)

Demystifying Video Reasoning
por: Wang, Ruisi, et al.
Publicado: (2026)

The Philosophical Foundations of Growing AI Like A Child
por: Luo, Dezhi, et al.
Publicado: (2025)

SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models
por: Fang, Hengyu, et al.
Publicado: (2025)

Object-Centric Vision Token Pruning for Vision Language Models
por: Li, Guangyuan, et al.
Publicado: (2025)

Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks
por: Zhang, Yunqi, et al.
Publicado: (2024)

VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
por: Wang, Sibo, et al.
Publicado: (2024)

Rethinking the Simulation vs. Rendering Dichotomy: No Free Lunch in Spatial World Modelling
por: Luo, Dezhi, et al.
Publicado: (2025)

Physical Prompt Injection Attacks on Large Vision-Language Models
por: Ling, Chen, et al.
Publicado: (2026)

Challenges and Trends in Egocentric Vision: A Survey
por: Li, Xiang, et al.
Publicado: (2025)

EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
por: Yang, Ruihan, et al.
Publicado: (2025)

GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing
por: Xiao, Yisong, et al.
Publicado: (2024)

Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems
por: Zhang, Jie, et al.
Publicado: (2025)

Uncovering Bias in Large Vision-Language Models with Counterfactuals
por: Howard, Phillip, et al.
Publicado: (2024)

EgoSim: Egocentric World Simulator for Embodied Interaction Generation
por: Hao, Jinkun, et al.
Publicado: (2026)

Adversarial Prompt Distillation for Vision-Language Models
por: Luo, Lin, et al.
Publicado: (2024)

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
por: Zhang, Xinwei, et al.
Publicado: (2026)

Cognitively-Inspired Tokens Overcome Egocentric Bias in Multimodal Models
por: Leonard, Bridget, et al.
Publicado: (2026)

FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models
por: Luo, Hanjun, et al.
Publicado: (2024)

EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models
por: Yuan, Botai, et al.
Publicado: (2025)

ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
por: Wang, Qineng, et al.
Publicado: (2025)

Freeze and Reveal: Exposing Modality Bias in Vision-Language Models
por: Kavuri, Vivek Hruday, et al.
Publicado: (2025)

VLADriver-RAG: Retrieval-Augmented Vision-Language-Action Models for Autonomous Driving
por: Zhao, Rui, et al.
Publicado: (2026)

The Point, the Vision and the Text: Does Point Cloud Boost Spatial Reasoning of Large Language Models? A Bias-Controlled Study
por: Zhang, Weichen, et al.
Publicado: (2025)

Can 3D Vision-Language Models Truly Understand Natural Language?
por: Deng, Weipeng, et al.
Publicado: (2024)

MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image
por: Song, Shezheng, et al.
Publicado: (2024)

Text-driven Affordance Learning from Egocentric Vision
por: Yoshida, Tomoya, et al.
Publicado: (2024)

BiasICL: In-Context Learning and Demographic Biases of Vision Language Models
por: Xu, Sonnet, et al.
Publicado: (2025)

Holmes: Towards Effective and Harmless Model Ownership Verification to Personalized Large Vision Models via Decoupling Common Features
por: Zhu, Linghui, et al.
Publicado: (2025)

Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models
por: Liu, Shaonan, et al.
Publicado: (2026)

GeoWorld-VLM: Geometry from World Models for Vision-Language Models
por: Gu, Renjie, et al.
Publicado: (2026)

Training-Free Unsupervised Prompt for Vision-Language Models
por: Long, Sifan, et al.
Publicado: (2024)