AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning

Zhen Zeng, Leijiang Gu, Zhangling Duan, Feng Li, Zenglin Shi, Cees Snoek, Meng Wang

ECCV 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Machine unlearning by selective forgetting · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add retaining-anchor masking (directional conflict and relative magnitude) to MFA (ablation)SMFA · S-MLLMUn Bench (LLaVA-OneVision, 5% forget)Retain-set image memory ROUGE-L: 0.486 -> 0.622Improved
add retaining-anchor masking to MFA (ablation)SMFA · S-MLLMUn Bench (LLaVA-OneVision, 10% forget)Retain-set image understanding ROUGE-L: 0.530 -> 0.634Improved
add retaining-anchor masking to MFA (ablation)SMFA · S-MLLMUn Bench (LLaVA-OneVision, 10% forget)Forget-set image memory ROUGE-L: 0.198 -> 0.493Hurt
add retaining-anchor masking to MFA (ablation)SMFA · S-MLLMUn Bench (LLaVA-OneVision, 5% forget)Forget-set image understanding ROUGE-L: 0.629 -> 0.655Improved
add relative magnitude mask to directional conflict mask (ablation)SMFA · S-MLLMUn Bench (LLaVA-OneVision, 5% forget)Forget-set image memory ROUGE-L: 0.641 -> 0.460Improved
add directional conflict mask to relative magnitude mask (ablation)SMFA · S-MLLMUn Bench (LLaVA-OneVision, 5% forget)Forget-set image memory ROUGE-L: 0.637 -> 0.460Improved
add relative magnitude mask to directional conflict mask (ablation)SMFA · S-MLLMUn Bench (LLaVA-OneVision, 10% forget)Forget-set text memory ROUGE-L: 0.744 -> 0.566Improved
add both masks versus single mask (ablation)SMFA · S-MLLMUn Bench (LLaVA-OneVision, 5% forget)Retain-set image memory ROUGE-L: 0.682 -> 0.622Hurt
increase masking hyperparameter k (ablation)SMFA · S-MLLMUn Bench (LLaVA-OneVision, 5% forget) and 10%forget-set ROUGE-LImproved
SMFA vs IDK Tuning under LLaVA 5% overall memory ROUGE-LSMFA · S-MLLMUn Bench (LLaVA-OneVision, 5% forget)Overall memory ROUGE-L: 0.121 -> 0.199Improved
SMFA vs IDK Tuning under full fine-tuning, retain image understandingSMFA · S-MLLMUn Bench (LLaVA-OneVision, 5% forget) (full fine-tuning)Retain-set image understanding ROUGE-L: 0.105 -> 0.640Improved
apply Distractors prompt attack to SMFASMFA · S-MLLMUn Bench (LLaVA-OneVision, 5% forget)Forget-set image memory ROUGE-L: 0.460 -> 0.385Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy