GraSLA: A Lightweight Spatial-Language-Action Model with Grasp Hypotheses as Geometric Priors
cs.RO
Submitted: 2026-11-11
Updated: 2026-11-17
Code: https://github.com/Minakanmi-Yuki/GraSLA
Terminology
Sources
- VLA-0: Building State-of-the-Art VLAs with Zero Modification
- Spatial RoboGrasp: Generalized Robotic Grasping Control Policy
- PointVLA: Injecting the 3D World into Vision-Language-Action Models
- GPA-RAM: Grasp-Pretraining Augmented Robotic Attention Mamba for Spatial Task Learning
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- GeoVLA: Empowering 3D Representations in Vision-Language-Action Models
- GraspGPT: Leveraging Semantic Knowledge from a Large Language Model for Task-Oriented Grasping
- TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
- Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation
- Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation