arXiv Computer Vision
SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
2d ago
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...
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.
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...
arXiv AI
Aug 25
Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality
The paper introduces ADU, a fine‑grained training framework that unlearns sensitive information from large language models by decoupling contextual attention pathways instead of erasing tokens. ADU exploits the distinction between local and global attention heads to identify and suppress attention paths that retrieve persistent sensitive anchors, while preserving local‑attention structure and overall language modeling performance. Evaluation on the TOFU and WMDP benchmarks shows ADU achieves superior forget quality (0.93 on TOFU) and retains 92.9% of model utility compared to 81.9% for existing baselines, with fewer side effects in benign contexts.
arXiv Computation and Language
Aug 31
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 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.