Correcting WHERE, Preserving HOW: Compositional Generalization for Vision-Language-Action Models via Referential Guidance

arXiv:2609.38616 · cs.RO, cs.CV, cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.RO, cs.CV, cs.LG

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Grounding — 33× in this paper · explained in 3 episodes
• Generalization — 16× in this paper · explained in 13 episodes
• Steering — 11× in this paper · explained in 2 episodes
• Compositional Generalization — 8× in this paper · explained in 4 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Alignment — 6× in this paper · explained in 1 episode
• Ablation — 5× in this paper · explained in 1 episode
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Affordance — 4× in this paper · explained in 1 episode
• Foundation Model — 4× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• VLA Models — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Vision-Language-Action (VLA) Models — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Action Expert Pretraining — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 3 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• IEEE International Conference on Robotics and Automation — 1× in this paper
• Inference-Time Steering — 1× in this paper · explained in 2 episodes
• Point Clouds — 1× in this paper · explained in 2 episodes
• Procedural Knowledge — 1× in this paper · explained in 2 episodes
• While Vision-Language-Action — 1× in this paper

Sources

• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
• Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models
• When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs
• LangGap: Diagnosing and Closing the Language Gap in Vision-Language-Action Models
• GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
• RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models
• VLAs are Confined yet Capable of Generalizing to Novel Instructions
• VLS: Steering Pretrained Robot Policies via Vision-Language Models
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• Unleashing More Actions via Action Compositional Training for VLA Models
• FAST: Efficient Action Tokenization for Vision-Language-Action Models
• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models
• Decoupling the Declarative from the Procedural in Vision-Language-Action Models
• Direct Action-Head Injection of A Grounded 3D Point Unlocks Spatial and Task Generalization
• Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Grounding
• Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification
• Inference-time Policy Steering via Vision and Touch
• Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation

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