Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs

arXiv:2609.29382 · cs.RO, cs.LG · Submitted 2026-09-24 · Read on arXiv

cs.RO, cs.LG

Submitted: 2026-09-24

Updated: 2026-09-29

Code: https://github.com/esgi-research-group/ee-vla

Terminology

• Transformer — 19× in this paper · explained in 2 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• KV cache — 12× in this paper · explained in 3 episodes
• Distillation — 6× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Action Space — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Latent Representation — 2× in this paper · explained in 2 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Vision-Language-Action (VLA) Models — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Adversarial Training — 1× in this paper · explained in 1 episode
• Affordance — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Flow Matching — 1× in this paper · explained in 7 episodes
• Flow-matching Vision-Language-Action — 1× in this paper
• Frozen model — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Lightweight Exit Transformers — 1× in this paper
• Mean Squared Error — 1× in this paper
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Speculative Decoding — 1× in this paper · explained in 2 episodes
• Vision-Language Model — 1× in this paper
• Vision-Language Model (VLM) — 1× in this paper · explained in 3 episodes

Sources

• A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model
• SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
• CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding

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