Cover Image

A Closed-Form Solution for Debiasing Vision-Language Models with Utility Guarantees Across Modalities and Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lian, Tangzheng, Hu, Guanyu, Ren, Yijing, Kollias, Dimitrios, Celiktutan, Oya
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CausalAffect: Causal Discovery for Facial Affective Understanding
by: Hu, Guanyu, et al.
Published: (2025)

Fair Domain Generalization: An Information-Theoretic View
by: Lian, Tangzheng, et al.
Published: (2025)

A Feature-level Bias Evaluation Framework for Facial Expression Recognition Models
by: Lian, Tangzheng, et al.
Published: (2025)

Unified Number-Free Text-to-Motion Generation Via Flow Matching
by: Huang, Guanhe, et al.
Published: (2026)

Grounding Emotion Recognition with Visual Prototypes: VEGA -- Revisiting CLIP in MERC
by: Hu, Guanyu, et al.
Published: (2025)

FairMT: Fairness for Heterogeneous Multi-Task Learning
by: Hu, Guanyu, et al.
Published: (2025)

Robust Facial Reactions Generation: An Emotion-Aware Framework with Modality Compensation
by: Hu, Guanyu, et al.
Published: (2024)

SAM2CLIP2SAM: Vision Language Model for Segmentation of 3D CT Scans for Covid-19 Detection
by: Kollias, Dimitrios, et al.
Published: (2024)

7th ABAW Competition: Multi-Task Learning and Compound Expression Recognition
by: Kollias, Dimitrios, et al.
Published: (2024)

Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyond
by: Kollias, Dimitrios, et al.
Published: (2024)

A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
by: Jung, Hoin, et al.
Published: (2024)

Rethinking Affect Analysis: A Protocol for Ensuring Fairness and Consistency
by: Hu, Guanyu, et al.
Published: (2024)

Bridging the Gap: Protocol Towards Fair and Consistent Affect Analysis
by: Hu, Guanyu, et al.
Published: (2024)

Domain adaptation, Explainability & Fairness in AI for Medical Image Analysis: Diagnosis of COVID-19 based on 3-D Chest CT-scans
by: Kollias, Dimitrios, et al.
Published: (2024)

MMA-MRNNet: Harnessing Multiple Models of Affect and Dynamic Masked RNN for Precise Facial Expression Intensity Estimation
by: Kollias, Dimitrios, et al.
Published: (2023)

Debiased Prompt Tuning in Vision-Language Model without Annotations
by: Jiang, Chaoquan, et al.
Published: (2025)

SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding
by: Yee, Phyo Thet, et al.
Published: (2025)

Uncertainty-guided Contrastive Learning for Single Source Domain Generalisation
by: Arsenos, Anastasios, et al.
Published: (2024)

Attention Debiasing for Token Pruning in Vision Language Models
by: Zhao, Kai, et al.
Published: (2025)

The 6th Affective Behavior Analysis in-the-wild (ABAW) Competition
by: Kollias, Dimitrios, et al.
Published: (2024)

Ensuring UAV Safety: A Vision-only and Real-time Framework for Collision Avoidance Through Object Detection, Tracking, and Distance Estimation
by: Karampinis, Vasileios, et al.
Published: (2024)

Common Corruptions for Enhancing and Evaluating Robustness in Air-to-Air Visual Object Detection
by: Arsenos, Anastasios, et al.
Published: (2024)

COVID-19 Computer-aided Diagnosis through AI-assisted CT Imaging Analysis: Deploying a Medical AI System
by: Gerogiannis, Demetris, et al.
Published: (2024)

A Vision-Based Closed-Form Solution for Measuring the Rotation Rate of an Object by Tracking One Point
by: Raviv, Daniel, et al.
Published: (2025)

Behaviour4All: in-the-wild Facial Behaviour Analysis Toolkit
by: Kollias, Dimitrios, et al.
Published: (2024)

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
by: Zhou, Guanyu, et al.
Published: (2024)

Interpretable Debiasing of Vision-Language Models for Social Fairness
by: An, Na Min, et al.
Published: (2026)

SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
by: Tang, Zhenwei, et al.
Published: (2025)

Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment
by: Zavras, Angelos, et al.
Published: (2024)

Seeing Beyond Redundancy: Task Complexity's Role in Vision Token Specialization in VLLMs
by: Hannan, Darryl, et al.
Published: (2026)

Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation Enhancement
by: Wang, Yuxuan, et al.
Published: (2024)

Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models
by: Xia, Yuexuan, et al.
Published: (2025)

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
by: Saini, Harshvardhan, et al.
Published: (2026)

Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant Analysis
by: Suchanek, Matej, et al.
Published: (2026)

Towards Real-world Debiasing: Rethinking Evaluation, Challenge, and Solution
by: Kuang, Peng, et al.
Published: (2024)

Debiased Fine-Tuning for Vision-language Models by Prompt Regularization
by: Zhu, Beier, et al.
Published: (2023)

Closed-Loop Bidirectional Prompting for Adversarial Robustness of Vision Language Models
by: Liu, Xiao, et al.
Published: (2026)

Delineating Knowledge Boundaries for Honest Large Vision-Language Models
by: Song, Junru, et al.
Published: (2026)

Vision-Language Models Create Cross-Modal Task Representations
by: Luo, Grace, et al.
Published: (2024)

Vision-Language Models for Vision Tasks: A Survey
by: Zhang, Jingyi, et al.
Published: (2023)