WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time

arXiv:2607.06988 · cs.RO, cs.AI · Submitted 2026-07-08 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-07-08

Updated: 2026-10-23

Terminology

• Steering — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 14 episodes
• Absorb — 1× in this paper · explained in 1 episode
• Foundation Models — 1× in this paper · explained in 7 episodes

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