- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
In this paper, the authors propose Mantis, the first Mamba-native PEFT framework for 3D PFMs. The authors identify the mismatch between existing Transformer-native PEFT methods and Mamba-based backbones, and address it through state-level adaptation and cross-serialization regularization. Extensive experiments demonstrate that Mantis achieves strong downstream performance while training less than 5% of the backbone parameters.
Critical strengths
- The motivation is clear, and the experiments are extensive.
- The paper inspires readers to propose parameter-efficient fine-tuning methods for Mamba-based works.
Critical weaknesses
-
Figure 2 is key to understanding Mantis's pipeline. However, the figure lacks necessary links between data streams, causing confusion and making it difficult to understand the overall pipeline of the proposed method after reading Section 3.1. Furthermore, Eq. (3) represents a residual connection, but in Figure 2, it is incorrectly shown as linked to S6 rather than ⊕. Additionally, it is recommended that the methodology illustrate, whenever possible, how each operator affects dimension, such as , to facilitate readers' understanding.
-
In the initial pipeline, Mantis is consistent with most previous related works. In terms of order indicators, differing from existing approaches that employ feature-wise affine transformations, the authors model the serialization order as a conditioning signal that modulates the representation in a residual manner. However, there is a lack of insight into this technical change.
-
SAA essentially modulates the frozen S6 parameters by encoding input signals for parameter-efficient fine-tuning. Why is it considered to integrate task-conditioned control signals into the Mamba state-space updates? It appears that DSCD is the one that integrates task-conditioned control signals.
-
The authors claim that the Hilbert and Trans-Hilbert curves capture complementary structural cues under different traversal orders. In fact, the Hilbert and Trans-Hilbert curves result from traversing the Hilbert curve in the xyz and yxz orders, respectively. Why are they complementary? Can xyz and zxy be complementary?
-
Since S6 possesses the property of unidirectional modeling, the Hilbert and Trans-Hilbert traversals are concatenated. When S6 performs state updates on the concatenated point sequence, are the authors considering that a single point in two different spatial relationships could cause structural confusion? Does this confusion affect the state-aware adaptation of SAA?
-
In Mamba3D, S6's bidirectional modeling operates at the channel level. How can Mantis be used to achieve efficient parameter tuning for Mamba3D?
-
The authors mention several recent outstanding works in the paper but do not compare them in Tables 1 & 2, such as PointGST[1].
[1] D. K. Liang, T. R. Feng, X. Zhou, Y. M. Zhang, Z. K. Zou, and X. Bai, ”Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 47, no. 12, pp. 10949--10966, Dec. 2025.
Questions for authors
Please see the Critical Weaknesses section.
13 comments
Q4: Why are Hilbert and Trans-Hilbert considered complementary?
A4: We thank the reviewer for raising this important question. We would like to clarify both the motivation for our serialization choice and the role of different traversal orders in Mantis.
Regarding the serialization choice, our design follows established practices in previous point cloud architectures. Specifically, PointMamba[1] (NeurIPS 2024) adopts Hilbert and Trans-Hilbert as two scanning strategies to provide different spatial locality perspectives. Similarly, Point Transformer V3[2] (CVPR 2024) explores multiple space-filling curve patterns and their axis-reordered variants, showing that changing the traversal-axis priority can provide alternative perspectives on spatial relationships. Following these works, we adopt Hilbert and Trans-Hilbert as an established and computationally efficient dual-serialization configuration, rather than claiming that the xyz/yxz combination is theoretically optimal among all possible axis permutations.
Regarding complementarity, different traversal orders produce different point arrangements and sequential contexts. Since Mamba performs order-sensitive state propagation, these different arrangements can induce distinct contextual representations. We agree that other permutations, such as xyz and zxy, could also provide complementary spatial perspectives in principle.
Importantly, the novelty of Mantis does not lie in introducing these serialization curves, but in how we exploit their complementary representations. Unlike simply using multiple serialization orders to diversify spatial contexts, our proposed DSCD explicitly enforces cross-order consistency at both the feature and prediction levels. This encourages the model to learn consistent semantic representations and task predictions despite variations in serialization order. Furthermore, Table 6(a) provides empirical support for our choice, showing that Hilbert and Trans-Hilbert achieve the best performance among the evaluated serialization combinations. We do not claim universal optimality over all possible axis permutations.
We sincerely thank the reviewer for this suggestion, which helps us better distinguish the role of established serialization strategies from the proposed DSCD contribution.
Q5: Does concatenating the two traversal sequences cause structural confusion or affect SAA?
A5: We sincerely thank the reviewer for raising this important concern. In our implementation, the Hilbert and Trans-Hilbert sequences are concatenated and processed by the S6 layers as a single continuous sequence without resetting the hidden state, following the established practice in PointMamba[1] (NeurIPS 2024). This design is intentional: rather than treating the two traversal orders independently, we allow the state accumulated from the first sequence to provide contextual information for processing the second sequence. The two sequences contain the same geometric points but have distinct order-aware representations and sequential neighborhoods. Therefore, their different spatial relationships reflect alternative traversal contexts rather than conflicting geometric observations.
For SAA, different sequential neighborhoods do not inherently undermine state-aware adaptation. Its controller dynamically generates modulation signals based on the current SSM input, intermediate features, and order-aware representation, allowing state updates to adapt to the actual context. Furthermore, DSCD enforces feature-level and prediction-level consistency across the two traversals, regularizing representation and prediction discrepancies induced by different serialization orders.
Q6: How can Mantis achieve parameter-efficient tuning for Mamba3D?
A6: We sincerely thank the reviewer for raising this question. We note that Mamba3D[3] employs two SSM branches: L+SSM performs forward modeling along the point-token dimension, while C-SSM operates on channel-flipped features to capture feature-level dependencies. The proposed SAA operates at the selective SSM parameter level rather than being tied to a specific sequence dimension. Consequently, Mantis can be extended to Mamba3D by incorporating SAA into both SSM branches. Each SAA generates control signals based on its respective branch inputs to modulate the corresponding selective SSM coefficients. This retains the original Bi-SSM architecture while freezing its backbone parameters and training only lightweight SAA modules and task-specific heads, thereby enabling parameter-efficient adaptation.
Q7: Could the authors include PointGST in Tables 1 and 2 for comparison?
A7: We sincerely thank the reviewer for this valuable suggestion. As discussed in Appendix C.3, we initially selected PMA as a representative PEFT baseline to keep the experimental comparisons focused. We had also included PointGST[4] (TPAMI 2025) in Table 3(c) to provide an additional comparison with existing PEFT methods. However, we acknowledge that this comparison was limited in scope and did not sufficiently cover the main classification and segmentation benchmarks. Following the reviewer's suggestion, we have further incorporated PointGST into Tables 1 and 2 of the revised manuscript, providing more comprehensive comparisons across different backbones and downstream tasks.
Object classification on ScanObjectNN and ModelNet40.
| Methods | Reference | #TP (M) | FLOPs (G) | OBJ_BG | OBJ_ONLY | PB_T50_RS | ModelNet40 |
|---|---|---|---|---|---|---|---|
| Point-MAE | ECCV22 | 22.1 (100%) | 4.8 | 90.02 | 88.29 | 85.18 | 93.8 |
| + PointGST | TPAMI25 | 0.6 (2.7%) | 4.8 | 91.74 (+1.72) | 90.19 (+1.90) | 85.29 (+0.11) | 93.5 (-0.3) |
| ReCon | ICML23 | 43.6 (100%) | 5.3 | 95.18 | 93.63 | 90.63 | 94.1 |
| + PointGST | TPAMI25 | 0.6 (1.4%) | 4.8 | 94.51 (-0.67) | 92.72 (-0.91) | 89.37 (-1.26) | 93.5 (-0.6) |
| PointMamba | NeurIPS24 | 12.3 (100%) | 3.1 | 94.32 | 92.60 | 89.31 | 93.6 |
| + PointGST | TPAMI25 | 0.6 (4.9%) | 4.5 | 93.21 (-1.11) | 91.77 (-0.83) | 86.93 (-2.38) | 93.5 (-0.1) |
| + Mantis (Ours) | This Paper | 0.6 (4.9%) | 4.0 | 94.65 (+0.33) | 93.14 (+0.54) | 89.96 (+0.65) | 93.7 (+0.1) |
| Mamba3D | ACM MM24 | 16.9 (100%) | 3.9 | 93.12 | 92.08 | 92.05 | 94.7 |
| + PointGST | TPAMI25 | 0.6 (3.6%) | 4.6 | 92.08 (-1.04) | 90.42 (-1.66) | 87.38 (-4.67) | 94.2 (-0.5) |
| + Mantis (Ours) | This Paper | 0.8 (4.7%) | 4.0 | 93.29 (+0.17) | 92.77 (+0.69) | 93.48 (+1.43) | 94.7 (+0.0) |
| ZigzagPointMamba | NeurIPS25 | 12.3 (100%) | 3.1 | 94.15 | 92.10 | 88.65 | 93.2 |
| + PointGST | TPAMI25 | 0.6 (4.9%) | 5.1 | 93.53 (-0.62) | 90.72 (-1.38) | 85.04 (-3.61) | 93.3 (+0.1) |
| + Mantis (Ours) | This Paper | 0.6 (4.9%) | 4.5 | 94.02 (-0.13) | 93.27 (+1.17) | 90.11 (+1.46) | 93.7 (+0.5) |
Part segmentation on ShapeNetPart.
| Methods | Param. (M) | Inst.mIoU | Cls.mIoU |
|---|---|---|---|
| PointMamba | 12.2 | 85.3 | 82.6 |
| + PointGST | 0.6 | 85.0 (-0.3) | 82.5 (-0.1) |
| + Mantis (Ours) | 0.6 | 85.1 (-0.2) | 82.9 (+0.3) |
| Mamba3D | 15.5 | 85.6 | 83.6 |
| + PointGST | 0.6 | 84.1 (-1.5) | 82.8 (-0.8) |
| + Mantis (Ours) | 0.7 | 86.1 (+0.5) | 84.1 (+0.5) |
| ZigzagPointMamba | 12.2 | 85.8 | 84.2 |
| + PointGST | 0.6 | 84.4 (-1.4) | 82.1 (-2.1) |
| + Mantis (Ours) | 0.6 | 85.9 (+0.1) | 84.5 (+0.3) |
Indoor semantic segmentation on S3DIS Area 5 and ScanNet V2.
| Methods | Param. (M) | S3DIS mAcc | S3DIS mIoU | ScanNet VmIoU | ScanNet PmIoU |
|---|---|---|---|---|---|
| Point-MAE | 21.8 | 69.9 | 60.8 | 51.2 | 50.8 |
| + PointGST | 1.7 | 68.4 | 58.6 | 44.1 | 41.9 |
| PointMamba | 12.2 | 70.1 | 60.9 | 50.3 | 50.1 |
| + PointGST | 0.6 | 65.1 | 55.8 | 43.5 | 43.1 |
| + Mantis (Ours) | 0.6 | 69.3 | 59.8 | 49.8 | 49.5 |
| Mamba3D | 15.4 | 68.2 | 58.4 | 51.3 | 50.7 |
| + PointGST | 0.6 | 65.8 | 55.0 | 45.6 | 44.9 |
| + Mantis (Ours) | 0.7 | 68.0 | 58.1 | 50.4 | 50.0 |
Notably, the additional results reveal that PointGST does not consistently recover the full fine-tuning performance on Mamba-based backbones. This may be related to the architectural differences between Transformer-based feature interactions and Mamba's selective state-space modeling, as PointGST was originally designed to perform spectral-domain adaptation within Transformer layers rather than SSM state updates. These results further support the effectiveness of Mantis's direct modulation of selective SSM updates.
References
[1] D. Liang, X. Zhou, W. Xu, X. Zhu, Z. Zou, X. Ye, X. Tan, and X. Bai, “PointMamba: A Simple State Space Model for Point Cloud Analysis,” Advances in Neural Information Processing Systems (NeurIPS), 2024.
[2] X. Wu, L. Jiang, P.-S. Wang, Z. Liu, X. Liu, Y. Qiao, W. Ouyang, T. He, and H. Zhao, “Point Transformer V3: Simpler, Faster, Stronger,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
[3] X. Han, Y. Tang, Z. Wang, and X. Li, “Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model,” Proceedings of the 32nd ACM International Conference on Multimedia (ACM MM), 2024.
[4] D. Liang, T. Feng, X. Zhou, Y. Zhang, Z. Zou, and X. Bai, “Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025.
We appreciate your recognition of our clear motivation and extensive experimental validation. We hope the responses below will clarify your concerns.
A1: We thank the reviewer for these constructive suggestions. We acknowledge that the original Figure 2 did not sufficiently illustrate certain data connections and residual operations. We have revised the figure and provide the following clarifications.
(1) Data flow. We have added explicit arrows to Figure 2 to clarify the connections between modules and the overall information flow, making the pipeline easier to follow.
(2) Residual connection. The original illustration was intended to represent the residual formulation in Eq. (3), but the connection to the addition operator was not explicitly depicted, potentially causing ambiguity. Following the reviewer's suggestion, we have revised Figure 2 to explicitly show the residual path connecting to the addition operator (⊕), ensuring consistency between the figure and Eq. (3).
(3) Tensor dimensions. We have supplemented Sec. 3.1 with clearer tensor shapes and dimensional transformations for key operations. Furthermore, Sec. 3.2 already provides the dimensional definitions of the projection matrices and control signals in SAA. We hope these clarifications will facilitate readers' understanding of the methodology.
A2: We sincerely thank the reviewer for this insightful comment. We would like to clarify that our design is motivated by the different roles of serialization information in PointMamba and Mantis.
In PointMamba[1] (NeurIPS 2024) , order-specific affine transformations encode different serialization orders by directly scaling and shifting token features, allowing the Mamba backbone to distinguish different traversal patterns. This is an effective design for order identification. However, Mantis focuses on state-level adaptation with frozen pre-trained backbones, where serialization information is needed not only to distinguish traversal orders but also to guide the adaptation of state-space dynamics.
To this end, our residual formulation retains the original token features while introducing an input-dependent, order-conditioned correction. The resulting order-aware representation is then used as a conditioning signal for the SAA controller, which dynamically modulates the selective SSM coefficients. Therefore, the key motivation is not that residual transformations are inherently superior to affine transformations, but that our formulation is designed to support serialization-aware state adaptation rather than solely feature-level order identification.
We appreciate the reviewer for providing this opportunity to clarify the motivation behind our design choice.
A3: We sincerely thank the reviewer for this insightful comment. We apologize that the distinction between SAA and DSCD may not have been sufficiently clear. We would like to clarify that SAA and DSCD serve fundamentally different purposes.
Specifically, SAA generates input-dependent control signals, rather than relying on an explicit task embedding. Its controller takes the current SSM input, intermediate block features, and order-aware representation as inputs to generate control signals that modulate the selective SSM coefficients (B, C, and Δ). Importantly, the controller parameters are optimized under the downstream task objective, enabling the generated control signals to adapt to the requirements of different downstream tasks. Consequently, task-conditioned refers to the task-adapted controller parameters, rather than an explicit task embedding.
In contrast, DSCD serves as a training-time regularization mechanism that encourages cross-serialization consistency in feature representations and predictions. Although its loss can indirectly influence the optimization of SAA through joint training, DSCD does not generate or directly inject control signals into the SSM updates. SAA is responsible for state-level control, whereas DSCD regularizes cross-order consistency.