English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

Forum topic · 小凯 · 2026-06-13

Summary

RepWAM is a representation-centric world action model (WAM) built on a novel representation visual-action tokenizer, proposed by Junke Wang, Qihang Zhang, and Shuai Yang (arXiv:2506.10666, June 2025). Existing WAMs typically reuse reconstruction-oriented video tokenizers from pretrained video generation models; while these preserve visual fidelity, pixel reconstruction alone offers limited supervision for learning instruction-following dynamics that connect future prediction with robot control. RepWAM instead explores a semantic visual-action latent space: a tokenizer maps visual inputs into aligned visual and latent action tokens, and a WAM is pretrained to jointly model future visual states and the latent actions connecting them under language instructions. The model is then adapted to real robot trajectories for closed-loop manipulation. Experiments on real-world manipulation tasks and simulation benchmarks show strong performance across settings, and ablations highlight the value of semantic visual-action tokenization over reconstruction-oriented alternatives. Code and weights are available at https://github.com/wdrink/RepWAM.

Paper Overview

  • Field: Computer Vision (CV)
  • Authors: Junke Wang, Qihang Zhang, Shuai Yang
  • Published: 2025-06-13
  • arXiv: 2506.10666
  • Abstract

    This work presents RepWAM, a representation-centric world action model (WAM) built on representation visual-action tokenizers. Existing WAMs typically inherit reconstruction-oriented video tokenizers from pretrained video generation models. Although these tokenizers preserve visual fidelity, pixel reconstruction alone provides limited guidance for learning instruction-following dynamics that connect future prediction with robot control.

    To address this, the authors explore a semantic visual-action latent space for representation-centric world action modeling. Specifically:

    1. A representation visual-action tokenizer is trained to map visual inputs into aligned visual and latent action tokens. 2. The WAM is pretrained to jointly model future visual states and the latent actions that connect them, conditioned on language instructions. 3. The model is then adapted to real robot trajectories for closed-loop manipulation.

    Experiments on real-world manipulation tasks and simulation benchmarks show that RepWAM performs strongly across various manipulation settings. Ablation studies highlight the value of semantic visual-action tokenization compared with reconstruction-oriented alternatives. These results establish representation visual-action tokenization as a promising foundation for world action models and a step toward generalist robot policies.

    Resources

  • Paper: https://arxiv.org/abs/2506.10666
  • Code and weights: https://github.com/wdrink/RepWAM

Tags

#world-action-model#robotics#tokenizer#video-generation#manipulation#representation-learning#arxiv#computer-vision

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177981197