Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Models

arXiv:2605.03438 · cs.CV · Submitted 2026-05-05 · Read on arXiv

cs.CV

Submitted: 2026-05-05

Updated: 2026-10-13

Code: https://github.com/gzhhhhhhh/Mantis

License: http://creativecommons.org/licenses/by-nc-sa/4.0/

The gist: Pre-trained 3D point cloud foundation models (PFMs) have demonstrated strong transferability across diverse downstream tasks.

Terminology

Abstract

Pre-trained 3D point cloud foundation models (PFMs) have demonstrated 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 introduce a granularity mismatch between token-level adaptation and state-level sequence dynamics. Consequently, straightforward transfer of existing PEFT approaches to frozen Mamba backbones leads to substantial accuracy degradation and unstable optimization. To address this issue, we propose Mantis, the first Mamba-native PEFT framework for 3D PFMs. Specifically, a State-Aware Adapter (SAA) is introduced to inject lightweight task-conditioned control signals into selective state-space updates, enabling state-level adaptation while keeping the pre-trained backbone frozen. Moreover, different valid point cloud serializations are regularized by Dual-Serialization Consistency Distillation (DSCD), thereby reducing serialization-induced instability. Extensive experiments across multiple benchmarks demonstrate that Mantis achieves competitive performance while training less than 5% of the backbone parameters.

Sources

Related papers