Same Path, Less Time: Training-Free Fast Execution of Vision-Language-Action Models under Inference Latency
cs.RO, cs.LG
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Understanding Asynchronous Inference Methods for Vision-Language-Action Models
- SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Real-Time Execution of Action Chunking Flow Policies
- Training-Time Action Conditioning for Efficient Real-Time Chunking
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- LeRobot: An Open-Source Library for End-to-End Robot Learning
- AdaTempo: Learning Shared Relative Tempo from Demonstrations for Faster Robot Manipulation
- Mean-Flow based One-Step Vision-Language-Action
- Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- One Step Diffusion via Shortcut Models
- DemoSpeedup: Accelerating Visuomotor Policies via Entropy-Guided Demonstration Acceleration
- FreeSpeed: Training-Free Speed Control for Generative Robot Policies
- PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models
- FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunking
- TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies
- ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning
- OpenVLA: An Open-Source Vision-Language-Action Model
- Accelerating VLA Inference with Perturbation Informed Execution
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