arXiv Computation and Language August 31, 2026 By Wonjun Lee, Jaehyuk Jang, Kangwook Ko, Hee-Seon Kim, Changick Kim

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

Read the original on arXiv Computation and Language →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

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

Hugging Face Trending Papers

Oct 1

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

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 pre...

llms multimodal benchmarks

arXiv Computer Vision

Oct 2

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

arXiv:2610.01962v1 Announce Type: cross Abstract: The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of...

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

llms multimodal benchmarks

arXiv AI

Oct 15

Toward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models

arXiv:2608.01008v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can memorize and disclose sensitive information, motivating machine unlearning to remove designated knowle...

By Junkai Lin, Junkai Chen, Siqi Hou, Yuhao He, Ruiqi Liu, Chenhan Jin, Shengze Xu, Tieyong Zeng, Xiangyuan Lan

llms multimodal benchmarks safety

arXiv Computer Vision

Sep 7

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

ICM-Bench is a new benchmark for evaluating identity-centric reasoning in multimodal agents with long-term memory. It consists of 839 synthetic video clips totaling 141 minutes and 1,217 open-ended questions about six recurring adults in a one-year life album. The benchmark isolates the ability to maintain recurring person identities and reason over their cross-time relations, and compares various baseline systems, showing that while Gemini 3.1 Pro performs well overall, its accuracy drops on questions requiring long-term identity profiles.

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

llms agents nlp multimodal benchmarks

One email a morning, machine-written

Related stories

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

Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning

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

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

Toward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models

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