arXiv Computation and Language

AIM: Anchor Identity Features, Then Match for Multimodal Large Language Model Unlearning

The paper introduces AIM, a two‑stage approach for unlearning identity‑specific information from multimodal large language models (MLLMs) when retain images are not available at deletion time. AIM first anchors an identity‑forgetting target using a universal visual prompt, then aligns the vision encoder to this target under a Fisher‑based constraint. Experiments demonstrate that AIM effectively removes identity knowledge while preserving other visual perception capabilities and prior knowledge.

arXiv Computation and Language

Sep 1

Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language Models

arXiv:2608.30649v1 Announce Type: new Abstract: Removing a specific individual's information from multimodal large language models (MLLMs) is often needed after deployment, but existing methods rely...

By Kangwook Ko, Jaehyuk Jang, Wonjun Lee, Hee-Seon Kim, Changick Kim

llms multimodal safety

arXiv AI

Jun 29

Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning

arXiv:2511. 20196v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can inadvertently memorize privacy-sensitive information during training.

By Zhen Zeng, Leijiang Gu, Zhangling Duan, Feng Li, Cees G. M. Snoek, Meng Wang, Zenglin Shi

llms fine-tuning multimodal benchmarks safety

arXiv Computer Vision

1d ago

ICM-Bench: Person-Level Identity Reasoning in Multimodal Agents with Long-Term Memory

arXiv:2609.04438v1 Announce Type: new Abstract: Long-horizon multimodal agents should remember not only what happened but also who participated. This capability depends on linking recurring faces, vo...

By Shidu Ren, Yunze Liu, Xing Liu, Chi-Hao Wu, Enmin Zhou, Junxiao Shen

llms agents nlp multimodal benchmarks

Hugging Face Trending Papers

Aug 4

Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation

Vision-Language Models (VLMs), like Large Language Models (LLMs), may memorize sensitive, copyrighted, or harmful knowledge from their pretraining corpora. Removing such knowledge is essential for building trustworthy AI systems.

llms multimodal benchmarks

arXiv AI

Aug 5

Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation

arXiv:2608. 03791v1 Announce Type: new Abstract: Vision-Language Models (VLMs), like Large Language Models (LLMs), may memorize sensitive, copyrighted, or harmful knowledge from their pretraining corpora.

By Chunlin Liu, Junnian Chen, Haitong Jiang, Jianyu Zhao, Yingsen Pang, Jingchen Li, Jiabiao He, Youming Lu, Jinhe Bi, Yuntao Du

llms multimodal benchmarks

arXiv Computer Vision

Sep 1

PIU: Proximity-guided Identity Unlearning in ID-Conditioned Diffusion Models

arXiv:2605.22311v2 Announce Type: replace Abstract: Identity-conditioned diffusion models enable high-quality and identity-consistent face generation, but they also raise severe privacy concerns, as...

By Jose Edgar Hernandez Cancino Estrada, Mauro D\'iaz Lupone, \v{Z}iga Emer\v{s}i\v{c}, Vitomir \v{S}truc, Peter Peer, Darian Toma\v{s}evi\'c

rag diffusion fine-tuning benchmarks safety

arXiv AI

Jul 24

Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning

arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.

By Lorenzo Orsingher, Thomas De Min, Massimiliano Mancini, Davide Talon, Elisa Ricci

llms nlp fine-tuning multimodal benchmarks safety

arXiv AI

Jul 7

PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglement

arXiv:2607. 02897v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong capabilities, but they may memorize private information from web data, raising privacy concerns.

By Xianren Zhang, Delvin Ce Zhang, Dongwon Lee, Suhang Wang

llms multimodal benchmarks safety

arXiv AI

Sep 1

Parametric Multimodal User Memory: Storing What Captions Cannot Carry

arXiv:2608.28609v1 Announce Type: cross Abstract: A personalized agent needs a user memory: a persistent model of who its user is. Today it is almost always text -- transcripts and captions retrieved...

By Bojie Li, Noah Shi

llms agents multimodal

arXiv Machine Learning

Aug 13

LEMUR: Latent Entropy-aware Multimodal Unlearning via Visual-anchored Reasoning Redirection

arXiv:2608. 11691v1 Announce Type: new Abstract: Reinforcement-learning (RL) post-training equips multimodal large reasoning models (MLRMs) with exploratory chains of thought (CoT), substantially improving visual reasoning.

By Xinhao Zhong, Yuxia Qiao, Junhao Li, Hao Fang, Yi Sun, Bin Chen

rag reinforcement-learning multimodal safety

arXiv Machine Learning

Jun 8

Diagnosing Visual Ignorance in Vision-Language Models

arXiv:2606. 06890v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) frequently rely on language priors, producing confident answers that are weakly grounded in visual evidence.

By Runyu Zhou, Qi Zhang, Qixun Wang, Yisen Wang

llms multimodal benchmarks

arXiv Machine Learning

Jun 16

Understanding Cross-Modal Contributions in Continual Vision-Language Models: A Theoretical Perspective

arXiv:2606. 14883v1 Announce Type: cross Abstract: Continual vision-language models are commonly addressed through sequential fine-tuning; however, although this paradigm enables adaptation to new environments (tasks), it inherently emphasizes the contribution of previously learned environments (tasks) at the expense of the stability required to preserve previously acquired knowledge.

By Salimeh Sekeh, Mary Wisell

llms fine-tuning multimodal

Related stories