Imagen de Portada

Bias Beyond Demographics: Probing Decision Boundaries in Black-Box LVLMs via Counterfactual VQA

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Zaiying, Yamasaki, Toshihiko
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

Language-guided Detection and Mitigation of Unknown Dataset Bias
por: Zhao, Zaiying, et al.
Publicado: (2024)

Unified Vector Floorplan Generation via Markup Representation
por: Shiohara, Kaede, et al.
Publicado: (2026)

CE-FAM: Concept-Based Explanation via Fusion of Activation Maps
por: Kuroki, Michihiro, et al.
Publicado: (2025)

Auto-Comp: An Automated Pipeline for Scalable Compositional Probing of Contrastive Vision-Language Models
por: Sbrolli, Cristian, et al.
Publicado: (2026)

BSED: Baseline Shapley-Based Explainable Detector
por: Kuroki, Michihiro, et al.
Publicado: (2023)

Face2Diffusion for Fast and Editable Face Personalization
por: Shiohara, Kaede, et al.
Publicado: (2024)

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation
por: Tanji, Naoto, et al.
Publicado: (2025)

Spectral Probing of Feature Upsamplers in 2D-to-3D Scene Reconstruction
por: Xiao, Ling, et al.
Publicado: (2026)

A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation
por: Xiao, Ling, et al.
Publicado: (2026)

ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points
por: Okumura, Ryota, et al.
Publicado: (2025)

ExposeAnyone: Personalized Audio-to-Expression Diffusion Models Are Robust Zero-Shot Face Forgery Detectors
por: Shiohara, Kaede, et al.
Publicado: (2026)

DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation
por: Fang, Yingying, et al.
Publicado: (2024)

TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs
por: Zhang, Zijian, et al.
Publicado: (2025)

Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens
por: Zheng, Haohan, et al.
Publicado: (2025)

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

ADBA:Approximation Decision Boundary Approach for Black-Box Adversarial Attacks
por: Wang, Feiyang, et al.
Publicado: (2024)

Box-QAymo: Box-Referring VQA Dataset for Autonomous Driving
por: Etchegaray, Djamahl, et al.
Publicado: (2025)

Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQA
por: Jin, Ruinan, et al.
Publicado: (2026)

Joint Fusion and Encoding: Advancing Multimodal Retrieval from the Ground Up
por: Huang, Lang, et al.
Publicado: (2025)

Difficulty Controlled Diffusion Model for Synthesizing Effective Training Data
por: Wang, Zerun, et al.
Publicado: (2024)

From Obstacles to Resources: Semi-supervised Learning Faces Synthetic Data Contamination
por: Wang, Zerun, et al.
Publicado: (2024)

Language-Guided Self-Supervised Video Summarization Using Text Semantic Matching Considering the Diversity of the Video
por: Sugihara, Tomoya, et al.
Publicado: (2024)

Adversarial Training from Mean Field Perspective
por: Kumano, Soichiro, et al.
Publicado: (2025)

Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners
por: Kumano, Soichiro, et al.
Publicado: (2025)

Theoretical Understanding of Learning from Adversarial Perturbations
por: Kumano, Soichiro, et al.
Publicado: (2024)

Wide Two-Layer Networks can Learn from Adversarial Perturbations
por: Kumano, Soichiro, et al.
Publicado: (2024)

Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
por: Zhao, Zhiyuan, et al.
Publicado: (2023)

Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval
por: Xiao, Ling, et al.
Publicado: (2022)

EvolBA: Evolutionary Boundary Attack under Hard-label Black Box condition
por: Tajima, Ayane, et al.
Publicado: (2024)

Online Open-set Semi-supervised Object Detection with Dual Competing Head
por: Wang, Zerun, et al.
Publicado: (2023)

Mirai: Autoregressive Visual Generation Needs Foresight
por: Yu, Yonghao, et al.
Publicado: (2026)

Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation
por: Gaur, Manu, et al.
Publicado: (2024)

VidLBEval: Benchmarking and Mitigating Language Bias in Video-Involved LVLMs
por: Yang, Yiming, et al.
Publicado: (2025)

Reward Incremental Learning in Text-to-Image Generation
por: Wang, Maorong, et al.
Publicado: (2024)

Continual Distillation of Teachers from Different Domains
por: Michel, Nicolas, et al.
Publicado: (2026)

Dealing with Synthetic Data Contamination in Online Continual Learning
por: Wang, Maorong, et al.
Publicado: (2024)

DSAP: Analyzing Bias Through Demographic Comparison of Datasets
por: Dominguez-Catena, Iris, et al.
Publicado: (2023)

Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
por: Tan, Xuwei, et al.
Publicado: (2026)

SCOMatch: Alleviating Overtrusting in Open-set Semi-supervised Learning
por: Wang, Zerun, et al.
Publicado: (2024)

CoTBox-TTT: Grounding Medical VQA with Visual Chain-of-Thought Boxes During Test-time Training
por: Qian, Jiahe, et al.
Publicado: (2025)