# From Video Frames to Robot Meta-Frames: A Unified Latent Interface for World Action Models

**Authors:** Guoqiang Liang, Yiqi Lin, Yanzhe Chen, Kevin Yuchen Ma, Mike Zheng Shou  
**Published:** 10 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.14365) · [PDF](https://arxiv.org/pdf/2611.14365) · [Code](https://github.com/showlab/MetaWAM) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.14365.html)

## Key numbers

- **68.9%**: MetaWAM reaches 68.9% success while collapsing the per-signal frames into one and cutting inference latency by…
- **39%**: …reaches 68.9% success while collapsing the per-signal frames into one and cutting inference latency by 39%
- **85.0%**: and attains 85.0% success on three real-world Franka tasks

## Abstract

Pretrained video diffusion models (VDMs) offer a powerful foundation for World Action Models (WAMs), which jointly predict robot actions and future observations. Building such models requires injecting low-dimensional robot signals (e.g. proprioception, actions, and values) into a latent space shaped by natural videos, and a key design choice is the interface through which these signals enter: existing schemes treat it as a formatting detail, spending a separate latent frame on each signal or bolting on dedicated encoders and decoders. We argue that signal injection is instead a distribution-alignment problem: how well a representation matches the prior of the pretrained VDMs during denoising. Using the relative reconstruction error of a frozen VDM denoiser as a probe, we find that conventional spatial encodings sit far off this prior, whereas frequency-domain packing yields latents that the denoiser corrects far less. Motivated by this diagnostic result, we propose MetaWAM, which folds all robot signals into a single unified meta-frame: each signal is assigned to a disjoint frequency-domain channel band and lifted to the spatial latent by an inverse DCT, yielding a decodable interface aligned with the pretrained VDM prior without any added module or architectural change. A fixed band layout together with slot-aware routing lets the same meta-frame support policy, world-model, and value prediction over a shared set of robot variables. On RoboCasa, MetaWAM reaches 68.9% success while collapsing the per-signal frames into one and cutting inference latency by 39%, and attains 85.0% success on three real-world Franka tasks. Code and models are available at https://github.com/showlab/MetaWAM

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.