DIMoE-Adapters uses self-calibrated expert evolution and prototype-guided selection to dynamically grow and allocate experts, outperforming prior continual learning methods on vision-language models.
Dualprompt: Complementary prompting for rehearsal-free continual learning
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
-
DIMoE-Adapters: Dynamic Expert Evolution for Continual Learning in Vision-Language Models
DIMoE-Adapters uses self-calibrated expert evolution and prototype-guided selection to dynamically grow and allocate experts, outperforming prior continual learning methods on vision-language models.