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

- Source: PKU EPIC Lab
- Published: 2026-07-08T04:23:22.000Z
- RoboHot: https://robohot.news/en/items/le12bmq72b4k63dtrd5xzx4tq
- Original: https://arxiv.org/abs/2607.06988

## Summary

PKU EPIC Lab proposes WAM-TTT, a test-time training framework that steers world-action models from raw human videos without robot actions, human-side annotations, or task-specific fine-tuning. The method absorbs human videos into a lightweight adaptive memory inside a frozen WAM through self-supervised video prediction, and uses a meta-training stage with paired human-robot data and a key-value memory reconstruction objective to align human demonstrations with robot behaviors. Experiments show it consistently outperforms in-context human-video conditioning baselines across diverse manipulation tasks and generalization settings.

## Why it matters

The original work proposes a method for adapting a frozen world-action model at test time using only unlabeled human videos, without robot demonstrations or fine-tuning, offering methodological reference value for researchers who want to reuse it.