Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models
cs.RO
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/park-jungin/spark-vla
Terminology
Sources
- GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model
- Qwen2.5-VL Technical Report
- 3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models
- RT-1: Robotics Transformer for Real-World Control at Scale
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- OpenVLA: An Open-Source Vision-Language-Action Model
- Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
- SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
- Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding
- What Matters in Building Vision-Language-Action Models for Generalist Robots
- Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference
- Language Conditioned Imitation Learning over Unstructured Data
- SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
- Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
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