P3T: Prototypical Point-level Prompt Tuning with Enhanced Generalization for 3D Vision-Language Models

ArXi:2604.15703v1 Announce Type: new With the rise of pre-trained models in the 3D point cloud domain for a wide range of real-world applications, adapting them to downstream tasks has become increasingly important. However, conventional full fine-tuning methods are computationally expensive and storage-intensive. Although prompt tuning has emerged as an efficient alternative, it often suffers from overfitting, thereby compromising generalization capability.