Paper Overview
- Field: Computer Vision (CV)
- Authors: Junke Wang, Qihang Zhang, Shuai Yang
- Published: 2025-06-13
- arXiv: 2506.10666
- Paper: https://arxiv.org/abs/2506.10666
- Code and weights: https://github.com/wdrink/RepWAM
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, they train a representation visual-action tokenizer that maps visual inputs into aligned visual and latent action tokens. They then pretrain the WAM to jointly model future visual states and the latent actions that connect them (conditioned on language instructions), and subsequently adapt it to real robot trajectories for closed-loop manipulation.
Results
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 to 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.