SCULPT-VLA: Learning Structured Control through Staged Action Grounding
cs.RO
Submitted: 2026-09-20
Updated: 2026-09-20
Comments: 31 pages, 25 figures, 16 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen3-VL Technical Report
- Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
- Bridge-WA: Learning Action-Relevant World Dynamics for Robotic Manipulation
- Motus: A Unified Latent Action World Model
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- Seeing Space and Motion: Enhancing Latent Actions with Geometric and Dynamic Awareness for Vision-Language-Action Models
- Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
- When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs
- Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models
- ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
- Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
- Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models
- OpenVLA: An Open-Source Vision-Language-Action Model
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with 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
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies