RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models
cs.RO
Submitted: 2026-09-28
Updated: 2026-09-28
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- 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
- Training-Time Action Conditioning for Efficient Real-Time Chunking
- Falcon: Fast Visuomotor Policies via Partial Denoising
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control
- CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
- Reflex: Real-Time VLA Control through Streaming Inference
- Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories
- OpenVLA: An Open-Source Vision-Language-Action Model
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
- Flow Matching for Generative Modeling
- Learning Native Continuation for Action Chunking Flow Policies
- FASTER: Rethinking Real-Time Flow VLAs
- Running VLAs at Real-time Speed
- Rolling Diffusion Models
- Leave No Observation Behind: Real-time Correction for VLA Action Chunks
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