Is User Feedback Always Informative? Retrieval Latent Defending for Semi-supervised Domain Adaptation Without Source Data
This paper aims to adapt the source model to the target environment, leveraging small user
feedback (ie., labeled target data) readily available in real-world applications. We find that …
feedback (ie., labeled target data) readily available in real-world applications. We find that …
Parameter-efficient Tuning of Pretrained Visual-Language Models in Multitask Robot Learning
Multimodal pretrained visual-language models (pVLMs) have showcased excellence across
several applications, like visual question-answering. Their recent application for policy …
several applications, like visual question-answering. Their recent application for policy …