Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning

arXiv:2610.10358 · cs.AI · Submitted 2026-10-07 · Read on arXiv

cs.AI

Submitted: 2026-10-07

Updated: 2026-10-13

Sources

Qwen2.5-VL Technical Report
Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
SineProject: Machine Unlearning for Stable Vision Language Alignment
PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models
Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models
Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
On the Robustness of Machine Unlearning for Vision-Language Models
Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation
Eight Methods to Evaluate Robust Unlearning in LLMs
Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character
Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
Gemma 3 Technical Report
Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models
Robust MLLM Unlearning via Visual Knowledge Distillation
From Learning to Unlearning: Biomedical Security Protection in Multimodal Large Language Models

Related papers