# Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation

arXiv: https://arxiv.org/abs/2605.21258 · HTML: https://mlsanity.com/paper/2605.21258/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 42 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 30 of 41)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [Reinforcement Learning with Augmented Data](https://mlsanity.com/paper/2004.14990/) (2020)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills](https://mlsanity.com/paper/2302.04659/) (2023)
- [MultiMAE: Multi-modal Multi-task Masked Autoencoders](https://mlsanity.com/paper/2204.01678/) (2022)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?](https://mlsanity.com/paper/2303.18240/) (2023)
- [Scaling Robot Learning with Semantically Imagined Experience](https://mlsanity.com/paper/2302.11550/) (2023)
- [RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking](https://mlsanity.com/paper/2309.01918/) (2023)
- [AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One](https://mlsanity.com/paper/2312.06709/) (2023)
- [Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2306.17817/) (2023)
- [RVT-2: Learning Precise Manipulation from Few Demonstrations](https://mlsanity.com/paper/2406.08545/) (2024)
- [iSDF: Real-Time Neural Signed Distance Fields for Robot Perception](https://mlsanity.com/paper/2204.02296/) (2022)
- [GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction](https://mlsanity.com/paper/2206.14735/) (2022)
- [PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm](https://mlsanity.com/paper/2310.08586/) (2023)
- [Robot Learning with Sensorimotor Pre-training](https://mlsanity.com/paper/2306.10007/) (2023)
- [Ponder: Point Cloud Pre-training via Neural Rendering](https://mlsanity.com/paper/2301.00157/) (2022)
- [Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation](https://mlsanity.com/paper/2411.18623/) (2024)
- [Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning](https://mlsanity.com/paper/2402.02500/) (2024)

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

- [Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization](https://mlsanity.com/paper/2610.05230/) (2026)

## Abstract (arXiv)

Current 3D-aware pretraining methods for embodied perception and manipulation are largely built on differentiable rendering frameworks, producing either fully implicit neural fields or fully explicit geometric primitives. Implicit representations, while expressive, lack explicit structural cues, whereas explicit ones preserve geometry but suffer from resolution limits and weak generalization. To address these limitations, we propose a novel pretraining framework that learns a hybrid representation-structural latent points. Specifically, we insert a point-wise latent variational autoencoder into the latent space of a point-cloud autoencoder, jointly regularizing point-wise features and coordinates toward a Gaussian prior. The resulting compact latent preserves coarse structural tendencies, which do not encode precise geometry but capture richer rough shape and semantic information, effectively combining the expressiveness of implicit representations with the structural priors of explicit ones. In addition, informed by shared design choices in prior work, we develop a streamlined, efficient 3DGS-based rendering pipeline that is deliberately kept lightweight, improving efficiency while leaving greater representational capacity to the front-end latent module. Extensive evaluations on RLBench, ManiSkill2, and a real-robot platform demonstrate consistent gains in task success, sample efficiency, and robustness to viewpoint and scene variations over strong baselines. Ablation studies further confirm that each component of our framework is critical to overall performance.