Existing evaluation suites tend to be limited, focusing on particular components or specialized use cases.

The Rashomon effect is a mixed blessing in responsible machine learning.

Existing backdoor defense methods typically require either homogeneous assumption, validation datasets, or client optimization conflicts.

Recently powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users world-wide.

Single-view 3D reconstruction methods like Triplane Gaussian Splatting (TGS) have enabled high-quality 3D model generation from just a single image input within seconds.

Public LLMs such as the Llama 2-Chat underwent alignment training and were considered safe. Recently Qi et al. [2024] reported that even benign fine-tuning on seemingly safe datasets can give rise to unsafe behaviors in the models.

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.