The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks

arXiv:2606.28529 · cs.RO, cs.AI, cs.CV · Submitted 2026-06-26 · Read on arXiv

cs.RO, cs.AI, cs.CV

Submitted: 2026-06-26

Updated: 2026-10-11

Terminology

• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Quantization — 1× in this paper · explained in 12 episodes

Sources

• OpenVLA: An Open-Source Vision-Language-Action Model
• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• RT-1: Robotics Transformer for Real-World Control at Scale
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
• RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
• Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
• Causal World Modeling for Robot Control
• World Action Models are Zero-shot Policies
• GigaWorld-Policy: An Efficient Action-Centered World--Action Model
• PaliGemma: A versatile 3B VLM for transfer
• Cosmos World Foundation Model Platform for Physical AI
• Mastering Diverse Domains through World Models
• QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
• VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
• SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
• SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
• DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
• One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation
• VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference

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