2 papers
cs.LG2025
Approximate Domain Unlearning for Vision-Language Models
Kodai Kawamura, Yuta Goto, Rintaro Yanagi +2
Pre-trained Vision-Language Models (VLMs) exhibit strong generalization capabilities, enabling them to recognize a wide range of objects across diverse domains without additional t…
cs.LG2024
Black-Box Forgetting
Yusuke Kuwana, Yuta Goto, Takashi Shibata +1
Large-scale pre-trained models (PTMs) provide remarkable zero-shot classification capability covering a wide variety of object classes. However, practical applications do not alway…