# Rethinking Point Clouds as Sequences: A Causal Next-Token Predictive Learning Framework

arXiv: https://arxiv.org/abs/2605.17566 · HTML: https://mlsanity.com/paper/2605.17566/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 52 references that are in the map.
- First posted on arXiv 17 May 2026.

## Builds on (most cited first, 30 of 33)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [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)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding](https://mlsanity.com/paper/2212.05171/) (2022)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [Unsupervised Point Cloud Pre-Training via Occlusion Completion](https://mlsanity.com/paper/2010.01089/) (2020)
- [Masked Discrimination for Self-Supervised Learning on Point Clouds](https://mlsanity.com/paper/2203.11183/) (2022)
- [Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders](https://mlsanity.com/paper/2212.06785/) (2022)
- [MVTN: Multi-View Transformation Network for 3D Shape Recognition](https://mlsanity.com/paper/2011.13244/) (2020)
- [Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?](https://mlsanity.com/paper/2212.08320/) (2022)
- [PointGPT: Auto-regressively Generative Pre-training from Point Clouds](https://mlsanity.com/paper/2305.11487/) (2023)
- [P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting](https://mlsanity.com/paper/2208.02812/) (2022)
- [Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training](https://mlsanity.com/paper/2302.14007/) (2023)
- [Point Cloud Pre-training with Diffusion Models](https://mlsanity.com/paper/2311.14960/) (2023)
- [Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders](https://mlsanity.com/paper/2312.10726/) (2023)
- [Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models](https://mlsanity.com/paper/2307.14971/) (2023)
- [PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders](https://mlsanity.com/paper/2408.08753/) (2024)
- [Next-Embedding Prediction Makes Strong Vision Learners](https://mlsanity.com/paper/2512.16922/) (2025)
- [Self-supervised Modal and View Invariant Feature Learning](https://mlsanity.com/paper/2005.14169/) (2020)

## Built on by (most cited first, 1 of 1)

- [Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners](https://mlsanity.com/paper/2608.19863/) (2026)

## Abstract (arXiv)

With the rapid progress of multimodal foundation models and predictive pre-training, an important open question is how to equip 3D point clouds with a pre-training paradigm that is better aligned with next-token and next-embedding learning. Existing point-cloud self-supervised methods are largely built on masked reconstruction or explicit geometric generation, and thus remain tied to input recovery rather than predictive dependency modeling. In this paper, we introduce PointNTP, which reformulates point cloud pre-training as a fully causal, decoder-free latent Next-Token Prediction problem. Specifically, each point cloud is first partitioned into local patches and serialized into a structured 3D token sequence according to patch-center geometry. The resulting sequence is then modeled by a causal Transformer under prefix-only conditioning, and trained with a shift-based prediction objective stabilized by stop-gradient targets. This design enables the model to learn structural dependencies directly in latent space, without reconstruction decoders or explicit geometric recovery. Extensive experiments demonstrate that the proposed PointNTP is highly competitive across multiple downstream tasks: it achieves 93.8%(+0.5%), 92.6%(+0.3%), and 89.3%(+1.1%) on OBJ_BG, OBJ_ONLY, and PB_T50_RS of ScanObjectNN, respectively; obtains 85.0%(+0.1%) in Cls.mIoU on ShapeNetPart; and reaches 71.1% mAcc on S3DIS Area 5. Overall, decoder-free causal latent prediction provides a simple, scalable, and potentially modality-agnostic paradigm for point-cloud self-supervised learning, offering a new 3D perspective on foundation-style predictive learning for 3D data.