# Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perception

arXiv: https://arxiv.org/abs/2602.23069 · HTML: https://mlsanity.com/paper/2602.23069/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 70 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 30 of 52)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2203.00680/) (2022)
- [ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning](https://mlsanity.com/paper/2206.13559/) (2022)
- [Geometric Dataset Distances via Optimal Transport](https://mlsanity.com/paper/2002.02923/) (2020)
- [AIM: Adapting Image Models for Efficient Video Action Recognition](https://mlsanity.com/paper/2302.03024/) (2023)
- [FLOT: Scene Flow on Point Clouds Guided by Optimal Transport](https://mlsanity.com/paper/2007.11142/) (2020)
- [MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences](https://mlsanity.com/paper/1910.09165/) (2019)
- [PointGPT: Auto-regressively Generative Pre-training from Point Clouds](https://mlsanity.com/paper/2305.11487/) (2023)
- [PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences](https://mlsanity.com/paper/2205.13713/) (2022)
- [Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models](https://mlsanity.com/paper/2304.07221/) (2023)
- [Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis](https://mlsanity.com/paper/2403.01439/) (2024)
- [Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning](https://mlsanity.com/paper/2410.08114/) (2024)

## Built on by (most cited first, 18 of 18)

- [Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement](https://mlsanity.com/paper/2603.08251/) (2026)
- [PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learning](https://mlsanity.com/paper/2603.23957/) (2026)
- [CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration](https://mlsanity.com/paper/2603.12721/) (2026)
- [PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference](https://mlsanity.com/paper/2603.22943/) (2026)
- [Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Models](https://mlsanity.com/paper/2605.03438/) (2026)
- [Diffusion Masked Pretraining for Dynamic Point Cloud](https://mlsanity.com/paper/2605.03639/) (2026)
- [Tri-Efficient Transfer Learning for Point Cloud Videos](https://mlsanity.com/paper/2606.24175/) (2026)
- [IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registration](https://mlsanity.com/paper/2603.12719/) (2026)
- [Pansharpening for Thin-Cloud Contaminated Remote Sensing Images: A Unified Framework and Benchmark Dataset](https://mlsanity.com/paper/2603.14952/) (2026)
- [Edit in 2D, Verify in 3D: Reinforcement Learning for Multi-view Consistent Scene Editing](https://mlsanity.com/paper/2603.03143/) (2026)
- [Parameter-Efficient Fine-Tuning for Spiking Point Cloud Models](https://mlsanity.com/paper/2607.29048/) (2026)
- [CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning](https://mlsanity.com/paper/2604.10973/) (2026)
- [GaussFusion: Towards Multimodal 3D Gaussian Pretraining](https://mlsanity.com/paper/2607.05906/) (2026)
- [Learnable Instance Attention Filtering for Adaptive Detector Distillation](https://mlsanity.com/paper/2603.26088/) (2026)
- [Again-Pose: Anchor-Guided Adaptive Inter-Frame Motion Cues Propagating for High-quality Human Pose Reconstruction](https://mlsanity.com/paper/2606.29230/) (2026)
- [Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understanding](https://mlsanity.com/paper/2608.30279/) (2026)
- [Partition-Invariant Tuning for 3D Scene Understanding](https://mlsanity.com/paper/2609.12473/) (2026)
- [SpikeOcc: Towards Resilient Multimodal 3D Occupancy Perception via Spiking Experts](https://mlsanity.com/paper/2610.15745/) (2026)

## Abstract (arXiv)

Point cloud video understanding is critical for robotics as it accurately encodes motion and scene interaction. We recognize that 4D datasets are far scarcer than 3D ones, which hampers the scalability of self-supervised 4D models. A promising alternative is to transfer 3D pre-trained models to 4D perception tasks. However, rigorous empirical analysis reveals two critical limitations that impede transfer capability: overfitting and the modality gap. To overcome these challenges, we develop a novel "Align then Adapt" (PointATA) paradigm that decomposes parameter-efficient transfer learning into two sequential stages. Optimal-transport theory is employed to quantify the distributional discrepancy between 3D and 4D datasets, enabling our proposed point align embedder to be trained in Stage 1 to alleviate the underlying modality gap. To mitigate overfitting, an efficient point-video adapter and a spatial-context encoder are integrated into the frozen 3D backbone to enhance temporal modeling capacity in Stage 2. Notably, with the above engineering-oriented designs, PointATA enables a pre-trained 3D model without temporal knowledge to reason about dynamic video content at a smaller parameter cost compared to previous work. Extensive experiments show that PointATA can match or even outperform strong full fine-tuning models, whilst enjoying the advantage of parameter efficiency, e.g. 97.21 % accuracy on 3D action recognition, +8.7 % on 4 D action segmentation, and 84.06% on 4D semantic segmentation.