DPW with a token-importance gating module and residual adapters achieves state-of-the-art performance in domain-class incremental learning for VLMs.
Learning transferable visual models from natural language supervision.arXiv preprint,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
A data-free pretraining step that places prompts in flatter loss regions improves calibration and performance when used as initialization for test-time prompt tuning of vision-language models.
citing papers explorer
-
Enhancing Continual Learning of Vision-Language Models via Dynamic Prefix Weighting
DPW with a token-importance gating module and residual adapters achieves state-of-the-art performance in domain-class incremental learning for VLMs.
-
Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining
A data-free pretraining step that places prompts in flatter loss regions improves calibration and performance when used as initialization for test-time prompt tuning of vision-language models.