Recent works demonstrate the performances of 3D point cloud recognition can be boosted remarkably by parameter-efficient prompt tuning. However, we observe that the improvement on downstream tasks comes at the expense of a severe drop in 3D domain generalization.

Instead of relying on the LLM itself to unlearn, we enforce an unlearned state during inference by employing a prompt classifier to identify and safeguard prompts to forget.

We employ a total of 26 annotators, consisting of 14 females and 12 males.

Traditional emotion analysis often takes a third-person perspective, limiting the ability of agents to interact naturally and empathetically.

We address this by proposing the B ayesian A ctive L earner for P reference M odeling (BAL-PM), a novel stochastic acquisition policy that not only targets points of high epistemic uncertainty according to the preference model but also seeks to maximize the entropy of the acquired prompt distribution in the feature space spanned by the employed LLM.

One concerning capability of these models is their ability to alter small attributes of an original image.