Urgent Actions Go First: Urgency-Aware Denoising for Real-Time VLA Control
cs.RO
Submitted: 2026-09-29
Updated: 2026-09-29
Comments: 19 pages
Code: https://github.com/ky-ji/BAC
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- Diffusion ReRoll: Revisable Denoising for Robotic Sequential Prediction
- vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models
- $\pi\mathbf{R}^2$: Reactive Real-time Flow Policies
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous Control
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation
- D3P: Dynamic Denoising Diffusion Policy via Reinforcement Learning
- Latent Diffusion Policy: Shaping Latent Spaces for Diffusion-Based 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
- 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