SOURCE-LINKED INTELLIGENCE

Not All Patches Are Equally Forgettable: Spatially Localized Domain Unlearning in Vision-Language Models

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Pre-trained vision-language models (VLMs) exhibit strong cross-domain recognition performance even without additional training. However, this robustness can also preserve undesirable domain-specific behavior, as domain-related and semantic information often remain entangled within the learned representation space, making selective domain unlearning challenging. Existing approaches typically address this problem through latent-space disentanglement and prompt- or feature-level interventions, without directly attributing and attenuating individual patch-token contributions. However, here we sugg

Read original source ↗ Open in workspace

recordType

paper

region

Global