ICPT adds an adaptive-length projection module and two geometric regularizations to enable efficient, high-accuracy personalization of LVLMs across complex multi-concept tasks.
arXiv preprint arXiv:2510.22765 (2025) 4
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Personalize Your Large Vision-language Models With In-context Prompt Tuning
ICPT adds an adaptive-length projection module and two geometric regularizations to enable efficient, high-accuracy personalization of LVLMs across complex multi-concept tasks.