# Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation

arXiv: https://arxiv.org/abs/2308.07931 · HTML: https://mlsanity.com/paper/2308.07931/

## Key facts

- Cited by 130 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 69 references that are in the map.
- First posted on arXiv 27 Jul 2023.

## Builds on (most cited first, 30 of 49)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics](https://mlsanity.com/paper/1703.09312/) (2017)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation](https://mlsanity.com/paper/2112.05124/) (2021)
- [Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations](https://mlsanity.com/paper/2209.03494/) (2022)
- [CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory](https://mlsanity.com/paper/2210.05663/) (2022)
- [Language-Driven Representation Learning for Robotics](https://mlsanity.com/paper/2302.12766/) (2023)

## Built on by (most cited first, 30 of 130)

- [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)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [ShapeLLM: Universal 3D Object Understanding for Embodied Interaction](https://mlsanity.com/paper/2402.17766/) (2024)
- [3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations](https://mlsanity.com/paper/2403.03954/) (2024)
- [Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis](https://mlsanity.com/paper/2312.08782/) (2023)
- [On Bringing Robots Home](https://mlsanity.com/paper/2311.16098/) (2023)
- [GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping](https://mlsanity.com/paper/2403.09637/) (2024)
- [Explore until Confident: Efficient Exploration for Embodied Question Answering](https://mlsanity.com/paper/2403.15941/) (2024)
- [Large Spatial Model: End-to-end Unposed Images to Semantic 3D](https://mlsanity.com/paper/2410.18956/) (2024)
- [Improving 2D Feature Representations by 3D-Aware Fine-Tuning](https://mlsanity.com/paper/2407.20229/) (2024)
- [Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation](https://mlsanity.com/paper/2404.01943/) (2024)
- [Language Models as Zero-Shot Trajectory Generators](https://mlsanity.com/paper/2310.11604/) (2023)
- [Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning](https://mlsanity.com/paper/2407.01531/) (2024)
- [Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction](https://mlsanity.com/paper/2409.18121/) (2024)
- [RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation](https://mlsanity.com/paper/2402.15487/) (2024)
- [EgoLifter: Open-world 3D Segmentation for Egocentric Perception](https://mlsanity.com/paper/2403.18118/) (2024)
- [GraspSplats: Efficient Manipulation with 3D Feature Splatting](https://mlsanity.com/paper/2409.02084/) (2024)
- [LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS](https://mlsanity.com/paper/2507.07136/) (2025)
- [Denoising Vision Transformers](https://mlsanity.com/paper/2401.02957/) (2024)
- [Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splatting](https://mlsanity.com/paper/2405.04378/) (2024)
- [Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations](https://mlsanity.com/paper/2408.04380/) (2024)
- [G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation](https://mlsanity.com/paper/2411.18369/) (2024)
- [4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models](https://mlsanity.com/paper/2503.10437/) (2025)
- [Learning Precise Affordances from Egocentric Videos for Robotic Manipulation](https://mlsanity.com/paper/2408.10123/) (2024)
- [Find Any Part in 3D](https://mlsanity.com/paper/2411.13550/) (2024)
- [Learning Generalizable Feature Fields for Mobile Manipulation](https://mlsanity.com/paper/2403.07563/) (2024)
- [What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models](https://mlsanity.com/paper/2512.03422/) (2025)
- [From Sora What We Can See: A Survey of Text-to-Video Generation](https://mlsanity.com/paper/2405.10674/) (2024)

## Abstract (arXiv)

Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization. Many robotic tasks, however, require a detailed understanding of 3D geometry, which is often lacking in 2D image features. This work bridges this 2D-to-3D gap for robotic manipulation by leveraging distilled feature fields to combine accurate 3D geometry with rich semantics from 2D foundation models. We present a few-shot learning method for 6-DOF grasping and placing that harnesses these strong spatial and semantic priors to achieve in-the-wild generalization to unseen objects. Using features distilled from a vision-language model, CLIP, we present a way to designate novel objects for manipulation via free-text natural language, and demonstrate its ability to generalize to unseen expressions and novel categories of objects.