Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D
cs.RO
Submitted: 2026-09-21
Updated: 2026-09-21
Project page: https://hustvl.github.io/Bridge3D
Terminology
Sources
- GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model
- GPT-4 Technical Report
- Qwen3-VL Technical Report
- PaliGemma: A versatile 3B VLM for transfer
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- RT-1: Robotics Transformer for Real-World Control at Scale
- 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
- InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
- Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
- GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data
- Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds
- VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
- 3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance
- MapAnything: Universal Feed-Forward Metric 3D Reconstruction
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- OpenVLA: An Open-Source Vision-Language-Action Model
- Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
- Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving