Cover Image

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tan, Zhangyun, Zhang, Zeliang, Liang, Susan, Tang, Yolo Yunlong, Chen, Lisha, Xu, Chenliang
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

Omni-Judge: Can Omni-LLMs Serve as Human-Aligned Judges for Text-Conditioned Audio-Video Generation?
by: Liang, Susan, et al.
Published: (2026)

MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness
by: Tang, Yolo Y., et al.
Published: (2025)

Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
by: Zhang, Zeliang, et al.
Published: (2025)

V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning
by: Hua, Hang, et al.
Published: (2024)

Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning
by: Yu, Zhenyu, et al.
Published: (2026)

CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion
by: Tang, Yolo Yunlong, et al.
Published: (2024)

Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?
by: Feng, Mingqian, et al.
Published: (2024)

Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding
by: Tang, Yolo Yunlong, et al.
Published: (2024)

Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
by: Liu, Jiani, et al.
Published: (2025)

Targeted Forgetting of Image Subgroups in CLIP Models
by: Zhang, Zeliang, et al.
Published: (2025)

Scaling Concept With Text-Guided Diffusion Models
by: Huang, Chao, et al.
Published: (2024)

Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?
by: Zhang, Zeliang, et al.
Published: (2024)

VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
by: Tang, Yolo Y., et al.
Published: (2024)

Why Instruction-Based Unlearning Fails in Diffusion Models?
by: Zhang, Zeliang, et al.
Published: (2026)

VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity
by: Bi, Jing, et al.
Published: (2025)

Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP
by: Zhang, Zeliang, et al.
Published: (2024)

Learning to Transform Dynamically for Better Adversarial Transferability
by: Zhu, Rongyi, et al.
Published: (2024)

Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination
by: Tang, Yolo Y., et al.
Published: (2025)

TDMM-LM: Bridging Facial Understanding and Animation via Language Models
by: Song, Luchuan, et al.
Published: (2026)

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

Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
by: Tang, Yolo Y., et al.
Published: (2025)

Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models
by: Deng, Kaiyuan, et al.
Published: (2026)

FreSca: Scaling in Frequency Space Enhances Diffusion Models
by: Huang, Chao, et al.
Published: (2025)

Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach
by: Bi, Jing, et al.
Published: (2024)

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)

Language-Guided Joint Audio-Visual Editing via One-Shot Adaptation
by: Liang, Susan, et al.
Published: (2024)

Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
by: Zhang, Zeliang, et al.
Published: (2024)

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
by: Deng, Kaiyuan, et al.
Published: (2026)

Training-Free Image Editing with Visual Context Integration and Concept Alignment
by: Song, Rui, et al.
Published: (2026)

ZeroSep: Separate Anything in Audio with Zero Training
by: Huang, Chao, et al.
Published: (2025)

High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling
by: Huang, Chao, et al.
Published: (2025)

LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning
by: Tang, Yolo Yunlong, et al.
Published: (2023)

Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Reward
by: Tang, Yolo Yunlong, et al.
Published: (2022)

Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models
by: Chen, Tianqi, et al.
Published: (2024)

Can you SPLICE it together? A Human Curated Benchmark for Probing Visual Reasoning in VLMs
by: Ballout, Mohamad, et al.
Published: (2025)

Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See
by: Zhang, Zeliang, et al.
Published: (2024)

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

Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning
by: Sanga, Prabhav, et al.
Published: (2025)

MedConcept: Unsupervised Concept Discovery for Interpretability in Medical VLMs
by: Haque, Md Rakibul, et al.
Published: (2026)

High-Quality Visually-Guided Sound Separation from Diverse Categories
by: Huang, Chao, et al.
Published: (2023)