Cover Image

Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Zhenyu, Zeng, Yangchen, Meng, Chunlei, Yao, Guangzhen, Zhou, Shuigeng
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning
by: Tan, Zhangyun, et al.
Published: (2026)

VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models
by: Ranjan, Ravi, et al.
Published: (2026)

Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting
by: Aylapuram, Sai Siddhartha Chary, et al.
Published: (2025)

Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models
by: Kwon, JuneHyoung, et al.
Published: (2026)

Selective Visual Prompting in Vision Mamba
by: Yao, Yifeng, et al.
Published: (2024)

Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting
by: Choi, Dasol, et al.
Published: (2024)

Can Multimodal Large Language Models Truly Understand Small Objects?
by: Han, Fujun, et al.
Published: (2026)

CLCR: Cross-Level Semantic Collaborative Representation for Multimodal Learning
by: Meng, Chunlei, et al.
Published: (2026)

Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols
by: Kim, Yongwoo, et al.
Published: (2025)

CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation
by: Yu, Zhenyu, et al.
Published: (2026)

Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
by: Fan, Chongyu, et al.
Published: (2024)

Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?
by: Chen, Shuo, et al.
Published: (2023)

Are Large Vision Language Models Truly Grounded in Medical Images? Evidence from Italian Clinical Visual Question Answering
by: Felizzi, Federico, et al.
Published: (2025)

Practical Continual Forgetting for Pre-trained Vision Models
by: Zhao, Hongbo, et al.
Published: (2025)

ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation
by: Yu, Zhenyu, et al.
Published: (2026)

ForgetMe: Evaluating Selective Forgetting in Generative Models
by: Yu, Zhenyu, et al.
Published: (2025)

Designing to Forget: Deep Semi-parametric Models for Unlearning
by: Zheng, Amber Yijia, et al.
Published: (2026)

AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models
by: Chen, Haokun, et al.
Published: (2025)

VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?
by: Zhao, Hongbo, et al.
Published: (2025)

Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks
by: Kwon, JuneHyoung, et al.
Published: (2026)

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

SSDA: Bridging Spectral and Structural Gaps via Dual Adaptation for Vision-Based Time Series Forecasting
by: Zhang, Mingrui, et al.
Published: (2026)

Benchmarking Unlearning for Vision Transformers
by: Zhao, Kairan, et al.
Published: (2026)

Deep Unlearning: Fast and Efficient Gradient-free Approach to Class Forgetting
by: Kodge, Sangamesh, et al.
Published: (2023)

Class Unlearning via Depth-Aware Removal of Forget-Specific Directions
by: Hatami, Arman, et al.
Published: (2026)

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
by: Tian, Bozhong, et al.
Published: (2024)

SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning
by: Wang, Ziqi, et al.
Published: (2024)

Mirage2Matter: A Physically Grounded Gaussian World Model from Video
by: Gao, Zhengqing, et al.
Published: (2026)

SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
by: Li, Qing, et al.
Published: (2025)

HarmoCLIP: Harmonizing Global and Regional Representations in Contrastive Vision-Language Models
by: Zeng, Haoxi, et al.
Published: (2025)

DIVER: Dynamic Iterative Visual Evidence Reasoning for Multimodal Fake News Detection
by: Zhou, Weilin, et al.
Published: (2026)

Characterizing Disparity Between Edge Models and High-Accuracy Base Models for Vision Tasks
by: Wang, Zhenyu, et al.
Published: (2024)

Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding
by: Xue, Haotian, et al.
Published: (2025)

Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
by: Jin, Hyundong, et al.
Published: (2026)

Can Vision-Language Models Solve Visual Math Equations?
by: Choudhury, Monjoy Narayan, et al.
Published: (2025)

LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model
by: Mei, Xiaodong, et al.
Published: (2026)

Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
by: Chen, Junkai, et al.
Published: (2026)

Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers
by: Stanić, Aleksandar, et al.
Published: (2024)

Robust MLLM Unlearning via Visual Knowledge Distillation
by: Wang, Yuhang, et al.
Published: (2025)

LLMs Can Compensate for Deficiencies in Visual Representations
by: Takishita, Sho, et al.
Published: (2025)