# PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learning

arXiv: https://arxiv.org/abs/2603.23957 · HTML: https://mlsanity.com/paper/2603.23957/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 25 Mar 2026.

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

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [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)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining](https://mlsanity.com/paper/2302.02318/) (2023)
- [Masked Discrimination for Self-Supervised Learning on Point Clouds](https://mlsanity.com/paper/2203.11183/) (2022)
- [Perception-R1: Pioneering Perception Policy with Reinforcement Learning](https://mlsanity.com/paper/2504.07954/) (2025)
- [PointGPT: Auto-regressively Generative Pre-training from Point Clouds](https://mlsanity.com/paper/2305.11487/) (2023)
- [Point Cloud Pre-training with Diffusion Models](https://mlsanity.com/paper/2311.14960/) (2023)
- [Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning](https://mlsanity.com/paper/2506.22624/) (2025)
- [Unsupervised Hyperspectral Image Super-Resolution via Self-Supervised Modality Decoupling](https://mlsanity.com/paper/2412.04802/) (2024)
- [Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring](https://mlsanity.com/paper/2601.13879/) (2026)
- [LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings](https://mlsanity.com/paper/2503.19740/) (2025)
- [PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning](https://mlsanity.com/paper/2602.23945/) (2026)
- [Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perception](https://mlsanity.com/paper/2602.23069/) (2026)
- [Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoning](https://mlsanity.com/paper/2512.00818/) (2025)
- [Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement](https://mlsanity.com/paper/2603.08251/) (2026)
- [PointDico: Contrastive 3D Representation Learning Guided by Diffusion Models](https://mlsanity.com/paper/2512.08330/) (2025)
- [ReCo-KD: Region- and Context-Aware Knowledge Distillation for Efficient 3D Medical Image Segmentation](https://mlsanity.com/paper/2601.08301/) (2026)
- [A Closer Look at Few-Shot 3D Point Cloud Classification](https://mlsanity.com/paper/2303.18210/) (2023)
- [Uni-NTFM: A Unified Foundation Model for EEG Signal Representation Learning](https://mlsanity.com/paper/2509.24222/) (2025)
- [CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration](https://mlsanity.com/paper/2603.12721/) (2026)
- [TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2512.03963/) (2025)
- [From Performance to Practice: Knowledge-Distilled Segmentator for On-Premises Clinical Workflows](https://mlsanity.com/paper/2601.09191/) (2026)
- [PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference](https://mlsanity.com/paper/2603.22943/) (2026)

## Built on by (most cited first, 10 of 10)

- [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)
- [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)
- [Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning](https://mlsanity.com/paper/2607.15736/) (2026)
- [Again-Pose: Anchor-Guided Adaptive Inter-Frame Motion Cues Propagating for High-quality Human Pose Reconstruction](https://mlsanity.com/paper/2606.29230/) (2026)
- [SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models](https://mlsanity.com/paper/2607.10296/) (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)

## Abstract (arXiv)

Understanding spatial dynamics and semantics in point cloud is fundamental for comprehensive 3D comprehension. While reinforcement learning algorithms such as Group Relative Policy Optimization (GRPO) have recently achieved remarkable breakthroughs in large language models by incentivizing reasoning capabilities through strategic reward design, their potential remains largely unexplored in the 3D perception domain. This naturally raises a pivotal question: Can RL-based methods effectively empower 3D point cloud fine-tuning? In this paper, we propose PointRFT, the first reinforcement fine-tuning paradigm tailored specifically for point cloud representation learning. We select three prevalent 3D foundation models and devise specialized accuracy reward and dispersion reward functions to stabilize training and mitigate distribution shifts. Through comprehensive few-shot classification experiments comparing distinct training paradigms, we demonstrate that PointRFT consistently outperforms vanilla supervised fine-tuning (SFT) across diverse benchmarks. Furthermore, when organically integrated into a hybrid Pretraining-SFT-RFT paradigm, the representational capacity of point cloud foundation models is substantially unleashed, achieving state-of-the-art performance particularly under data-scarce scenarios.