Knowing When to Stop: Adaptive Action Chunking via Internal Cross-Attention Dynamics in VLAs

arXiv:2609.00908 · cs.RO · Submitted 2026-09-01 · Read on arXiv

cs.RO

Submitted: 2026-09-01

Updated: 2026-09-16

Terminology

• Action Chunking — 21× in this paper · explained in 1 episode
• Attention Entropy — 7× in this paper · explained in 2 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Generalization — 5× in this paper · explained in 13 episodes
• Grounding — 5× in this paper · explained in 3 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• VLA Models — 4× in this paper · explained in 3 episodes
• Flow Matching — 3× in this paper · explained in 8 episodes
• Generalizability — 3× in this paper · explained in 6 episodes
• Closed-Loop Control — 2× in this paper · explained in 3 episodes
• Computational overhead — 2× in this paper · explained in 2 episodes
• Vision-Language-Action (VLA) Models — 2× in this paper · explained in 2 episodes
• Adaptability — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptive Strategy — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Digital Twin — 1× in this paper · explained in 4 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
• RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
• UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
• Gemini Robotics: Bringing AI into the Physical World
• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• Denoising Diffusion Implicit Models
• Flow Matching Guide and Code
• Flow Matching for Generative Modeling
• Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
• Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
• VLA Knows Its Limits: Adaptive Execution Horizons for Robot Policies
• Learning Native Continuation for Action Chunking Flow Policies
• OpenVLA: An Open-Source Vision-Language-Action Model
• X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• World Action Models are Zero-shot Policies
• Causal World Modeling for Robot Control

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