TPT does not explicitly align the pre-trained CLIP to become aware of the test sample distribution. For the effective test-time adaptation of V -L foundation models, it is crucial to bridge the distribution gap between the pre-training dataset and the downstream evaluation set for high zero-shot generalization.

AudioSet) has an even larger negative impact.

The learnt models in the latter domain can then be used for a diverse set of tasks in a zero-shot way, similar to "Contrastive Language-Image

However, developing models that can process weight-space objects is challenging due to their high dimensional nature.

Our work proposes P-Flow, a fast and data-efficient zero-shot TTS model that uses speech prompts for speaker adaptation. P-Flow comprises a speech-prompted text encoder for speaker adaptation and a flow matching generative decoder for high-quality and fast speech synthesis.