No article text was recorded for this version.
3D spatial grounding
Version 1 of 180 papers92 conceptsfrozen 2026-10-04
Papers in this version
- Blog: PointVLA: Injecting the 3D World into Vision-Language-Action Models
- Blog: PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation
- Blog: H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation
- Blog: RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effective
- Blog: Recent advances in diffusion-based embodied imitation learning: a survey
- Blog: VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation
- Blog: VGGT-DP: Generalizable Robot Control via Vision Foundation Models
- Blog: Autonomous planning based on spatial concepts to tidy up home environments with service robots
- Blog: RoboHiMan: A Hierarchical Evaluation Paradigm for Compositional Generalization in Long-Horizon Manipulation
- Blog: Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning
- Blog: SculptDiff: Learning Robotic Clay Sculpting from Humans with Goal Conditioned Diffusion Policy
- Blog: Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning
- Blog: ChainedDiffuser: Unifying Trajectory Diffusion and Keypose Prediction for Robotic Manipulation
- Blog: 3D-MVP: 3D Multiview Pretraining for Robotic Manipulation
- Blog: SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning
- Blog: Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
- Blog: UMIGen: A Unified Framework for Egocentric Point Cloud Generation and Cross-Embodiment Robotic Imitation Learning
- Blog: RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation
- Blog: FlowPolicy: Enabling Fast and Robust 3D Flow-Based Policy via Consistency Flow Matching for Robot Manipulation
- Blog: ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
- Blog: From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors
- Blog: DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation
- Blog: T3VIP: Transformation-based 3D Video Prediction
- Blog: Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives
- Blog: TesserAct: Learning 4D Embodied World Models
- Blog: JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation
- Blog: EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining
- Blog: Towards Fusing Point Cloud and Visual Representations for Imitation Learning
- Blog: Generalist Robot Manipulation beyond Action Labeled Data
- Blog: 3D-VLA: A 3D Vision-Language-Action Generative World Model
- Blog: PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation
- Blog: GWM: Towards Scalable Gaussian World Models for Robotic Manipulation
- Blog: General In-Hand Object Rotation with Vision and Touch
- Blog: EmbodiedMAE: A Unified 3D Multi-Modal Representation for Robot Manipulation
- Blog: DexH2R: A Benchmark for Dynamic Dexterous Grasping in Human-to-Robot Handover
- Blog: Generalizable Humanoid Manipulation with 3D Diffusion Policies
- Blog: GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulation
- Blog: 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
- Blog: 3D-DLP: Self-supervised 3D Object-centric Scene Representation Learning
- Blog: EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation
- Blog: LaST$_{0}$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
- Blog: SUGAR: Pre-training 3D Visual Representations for Robotics
- Blog: 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
- Blog: SEIL: Simulation-augmented Equivariant Imitation Learning
- Blog: CL3R: 3D Reconstruction and Contrastive Learning for Enhanced Robotic Manipulation Representations
- Blog: One Policy to Dress Them All: Learning to Dress People with Diverse Poses and Garments
- Blog: Embodied Language Grounding With 3D Visual Feature Representations
- Blog: RobotArena ∞: Scalable Robot Benchmarking via Real-to-Sim Translation
- Blog: Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning
- Blog: Part-Guided 3D RL for Sim2Real Articulated Object Manipulation
- Blog: THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation
- Blog: 3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks
- Blog: Spatial-Language Attention Policies for Efficient Robot Learning
- Blog: Unsupervised Learning of Visual 3D Keypoints for Control
- Blog: Learning 6-DOF Grasping Interaction via Deep Geometry-Aware 3D Representations
- Blog: PointPatchRL - Masked Reconstruction Improves Reinforcement Learning on Point Clouds
- Blog: Transporter Networks: Rearranging the Visual World for Robotic Manipulation
- Blog: Avi: A 3D Vision-Language Action Model Architecture generating Action from Volumetric Inference
- Blog: Data-Driven Grasp Synthesis - A Survey
- Blog: Reinforcement Learning with Generalizable Gaussian Splatting
Showing 60 of 80 papers.
History & citation
Current · Permanent link
- This direction split from 3D Spatial Grounding for Robotic Manipulation Policies (64% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_3d_spatial_grounding_2c14345a,
title = {3D spatial grounding},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/3d-spatial-grounding/rdr_2c14345a776e4be2b59903384998ae5b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_3d_spatial_grounding_2c14345a_v1,
title = {3D spatial grounding},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/3d-spatial-grounding/rdr_2c14345a776e4be2b59903384998ae5b/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}