Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks
cs.RO, cs.AI, cs.CV
Submitted: 2026-09-29
Updated: 2026-09-29
Project page: https://s1ghhh.github.io/staircase-policy
Terminology
Sources
- Understanding Asynchronous Inference Methods for Vision-Language-Action Models
- Motus: A Unified Latent Action World Model
- $\pi_0$: 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
- Genie: Generative Interactive Environments
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
- Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning
- LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
- StreamVLA: Breaking the Reason-Act Cycle via Completion-State Gating
- InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
- Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- Learning Universal Policies via Text-Guided Video Generation
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies
- Dreaming the Unseen: World Model-regularized Diffusion Policy for Out-of-Distribution Robustness
- NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models
- NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks
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