VLM Unlearning

VLM: Vision-Language Model

Vision-language model unlearning asks how to remove targeted information—such as sensitive identities, copyrighted content, or spurious associations—from models that connect images and text without losing useful capabilities. Methods include refusal fine-tuning and reinforcement learning, activation or representation editing, concept- and layer-selective updates, null-space constraints, and distillation. Evaluations use forget and retain sets across visual question answering, identity, concept, and domain tasks, increasingly testing cross-modal transfer, alternate prompts, recoverability, fairness, and collateral damage. A central challenge is that suppressing an answer may leave knowledge recoverable through another query or modality, while stronger or repeated edits can degrade general utility and multimodal alignment.

Latest papers

31 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning
Oct 1, 2026Si Qi Goh, Cap Dang Xuan Kiet, Tat-Jen Cham +1VLM Unlearning Privacy-Preserving Language Models
Digital Trust Centre, Nanyang Technological University, Singapore · College of Computing and Data Science, Nanyang Technological University, Singapore
Open Vocabulary Domain Unlearning
Sep 25, 2026Sumanth Udupa, Mehrtash Harandi, Yadan Luo +1VLM Unlearning Machine Unlearning
The University of Queensland · Monash University
Not All Patches Are Equally Forgettable: Spatially Localized Domain Unlearning in Vision-Language Models
Sep 15, 2026Akanksha Singh, Vinod K. KurmiVLM Unlearning Machine Unlearning
Indian Institute of Science Education and Research Bhopal, India
Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models
Aug 30, 2026Aditi Sarker, Nazreen Shah, Rafi Ibn Sultan +3VLM Evaluation VLM Unlearning
Department of Computer Science, Wayne State University, MI, USA · Department of Electronics & Communications Engineering, IIIT Delhi, India · Institute for AI and Data Science (AIDaS), Wayne State University, MI, USA
LEMUR: Latent Entropy-aware Multimodal Unlearning via Visual-anchored Reasoning Redirection
Aug 12, 2026Xinhao Zhong, Yuxia Qiao, Junhao Li +3VLM Unlearning Multimodal Large Language Models
3Pengcheng Laboratory · 1Harbin Institute of Technology, Shenzhen · 2Tsinghua University
Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation
Aug 4, 2026Chunlin Liu, Junnian Chen, Haitong Jiang +7VLM Evaluation VLM Unlearning
1Shenzhen University · 2Hebei University of Technology · 3Ludwig Maximilian University of Munich +1
Toward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models
Aug 2, 2026Junkai Lin, Junkai Chen, Siqi Hou +6VLM Unlearning Privacy Leakage in Language Models
Institute of Automation, Chinese Academy of Sciences · The Chinese University of Hong Kong · The Australian National University +3
Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
Jul 23, 2026Lorenzo Orsingher, Thomas De Min, Massimiliano Mancini +2VLM Unlearning Algorithmic Fairness
University of Trento, Trento, Italy · Fondazione Bruno Kessler, Trento, Italy
Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning
Jul 21, 2026Zijie Liu, Jinhao Duan, Gaowen Liu +2VLM Unlearning Vision-Language Models
UNC at Chapel Hill · Cisco Research · Michigan State University
One Modality to Forget Them All: Enhancing Cross-Modal Unlearning in Vision-Language Models
Jul 17, 2026Sudharshan Balaji, Yili Ren, Guangjing Wang +2VLM Unlearning VLM Robustness
University of South Florida · USA · University of Massachusetts Lowell
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Jul 8, 2026Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1VLM Unlearning MLLM Unlearning
University of Maryland, Baltimore County · University of Notre Dame · UNC Chapel Hill
MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs
Jun 11, 2026He Li, Haoang Chi, Qizhou Wang +6VLM Unlearning Multimodal Large Language Models
College of Computer Science and Technology, National University of Defense Technology, Changsha, China · TMLR Group, Hong Kong Baptist University, Hong Kong, China · School of Statistics and Data Science, Shanghai University of Finance and Economics, Shanghai, China +2
SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs
Jun 1, 2026Zhijing Zhang, Jiaqi Ding, Qianshan Wei +5VLM Unlearning Multimodal Large Language Models
School of Computer Science and Engineering, Southeast University · Institute of Automation, Chinese Academy of Sciences
On the Robustness of Machine Unlearning for Vision-Language Models
May 26, 2026Yujie Lin, Kaidi Jia, Jiayao Ma +2VLM Evaluation VLM Unlearning
1Xiamen University
Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
May 26, 2026Junkai Chen, Yuhao He, Junxiang You +3VLM Unlearning Multimodal Large Language Models
Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, UCAS
CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
May 18, 2026Shen Lin, Junhao Dong, Rongjie Chen +3VLM Unlearning Vision-Language Models
1Fujian Normal University · 2Nanyang Technological University · 3Xidian University
ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
May 15, 2026Jiahui Guang, Haiyan Wang, Yingjie Zhu +4VLM Unlearning Multimodal Large Language Models
Harbin Institute of Technology, Shenzhen, China · Peng Cheng Laboratory, Shenzhen, China · The Hong Kong Polytechnic University, Hong Kong, China +1
ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
May 14, 2026Shen Lin, Jing Lin, Junhao Dong +2VLM Unlearning MLLM Unlearning
1Fujian Normal University · 2Nanyang Technological University · University of New South Wales +1
PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models
May 9, 2026Jiahui Guang, Zexun Zhan, Zhenlin Xu +5VLM Evaluation VLM Unlearning
Harbin Institute of Technology, Shenzhen, China · Sichuan University, Chengdu, China · Harbin Institute of Technology, Weihai, China +3
Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models
May 8, 2026Kaidi Jia, Yujie Lin, Chengyi Yang +2VLM Unlearning Object Hallucination in VLMs
1Xiamen University
Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning
May 7, 2026Yuhang Wang, Zhenxing Niu, Haoxuan Ji +3VLM Unlearning Multimodal Large Language Models
School of Computer Science and Technology, Xidian University · Xi’an Jiaotong University
Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks
May 5, 2026JuneHyoung Kwon, MiHyeon Kim, Eunju Lee +3VLM Evaluation VLM Unlearning
Department of Artificial Intelligence, Chung-Ang University · KT Corporation · Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University
Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models
May 5, 2026JuneHyoung Kwon, JungMin Yun, YoungBin KimVLM Evaluation VLM Unlearning
Department of Artificial Intelligence, Chung-Ang University · Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University
Metric Unreliability in Multimodal Machine Unlearning: A Systematic Analysis and Principled Unified Score
May 4, 2026Abdullah Ahmad Khan, Hamid Laga, Ferdous SohelVLM Evaluation VLM Unlearning
Murdoch University
Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?
Apr 9, 2026Yunusa Haruna, Adamu Lawan, Ibrahim Haruna Abdulhamid +4Machine Unlearning VLM Unlearning
NewraLab, Suzhou, China · Beihang University · Beijing GoerTek Alpha Lab +3
VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models
Apr 5, 2026Ravi Ranjan, Agoritsa PolyzouVLM Unlearning Vision-Language-Action Models
Florida International University Miami, USA
Suppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMs
Apr 3, 2026Zhangyun Tan, Zeliang Zhang, Jiani Liu +4VLM Evaluation VLM Unlearning
University of Rochester
SALMUBench: A Benchmark for Sensitive Association-Level Multimodal Unlearning
Mar 27, 2026Cai Selvas-Sala, Lei Kang, Lluis GomezVLM Unlearning Machine Unlearning Evaluation
Computer Vision Center · Universitat Polit`ecnica de Catalunya · Universitat Aut`onoma de Barcelona
Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
Mar 23, 2026Hyundong Jin, Dongyoon Han, Eunwoo KimVLM Unlearning Machine Unlearning
Chung-Ang University · NAVER AI Lab
RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion Models
Mar 16, 2026Ravi Ranjan, Utkarsh Grover, Xiaomin Lin +1Machine Unlearning VLM Unlearning
Florida International University Miami, USA · University of South Florida Tampa, USA

Oct 1, 2026J/K move · Enter open · S save

SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning

Si Qi Goh, Cap Dang Xuan Kiet, Tat-Jen Cham, Kwok-Yan Lam

Digital Trust Centre, Nanyang Technological University, Singapore · College of Computing and Data Science, Nanyang Technological University, Singapore

VLM Unlearning Privacy-Preserving Language Models MLLM Unlearning Privacy Protection in VLMs Machine Unlearning

Open paper AskPDF arXiv

The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of personally identifiable information (PII) while preserving permitted knowledge about the same individual. This setting is challenging because both sensitive and retained information can share the same visual inputs and intermediate representations. We introduce SIEVE, a simple and effective framework for selective VLM unlearning. SIEVE directly regularizes attention-value representations while also controlling model outputs. SIEVE suppresses attention values for forget examples toward a constant zero, while preserving retain-example representations by matching them to a frozen reference model. These objectives are combined with sequence-level forget and retain supervision, enabling targeted forgetting without largely affecting retained knowledge. Extensive experiments show that SIEVE achieves state-of-the-art performance on unlearning with multiple model-modality settings, while maintaining competitive retained utility. Ablation studies further show that value suppression and negative cross-entropy contribute complementary forgetting signals, while reference-based value matching substantially reduces utility degradation. These results demonstrate that attention values provide an effective intervention point for selective multimodal unlearning when sensitive and retained knowledge are closely related.