R3D: Revisiting 3D Policy Learning
cs.CV, cs.RO
Submitted: 2026-04-16
Updated: 2026-09-20
Project page: https://r3d-policy.github.io
Terminology
Sources
- ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data
- 3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons
- Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation
- 3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation
- ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
- Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation
- 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- OpenVLA: An Open-Source Vision-Language-Action Model
- PointVLA: Injecting the 3D World into Vision-Language-Action Models
- Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
- BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
- Vision-Language Foundation Models as Effective Robot Imitators
- Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models