AI RESEARCH
Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Models
arXiv CS.CV
•
ArXi:2605.03438v1 Announce Type: new Pre-trained 3D point cloud foundation models (PFMs) have nstrated strong transferability across diverse downstream tasks. However, full fine-tuning these models is computationally expensive and storage-intensive. Parameter-efficient fine-tuning (PEFT) offers a promising alternative, but existing PEFT approaches are primarily designed for Transformer-based backbones and rely on token-level prompting or feature transformation. Mamba-based backbones