Not All Patches Are Equally Forgettable: Spatially Localized Domain Unlearning in Vision-Language Models
This story is from 2026-09-17. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.17790v1 Announce Type: new Abstract: 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…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-09-17 04:00 · arXiv cs.CV
Not All Patches Are Equally Forgettable: Spatially Localized Domain Unlearning in Vision-Language Models