RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

• URL: http://arxiv.org/abs/2606.13674v2
• Date: Sat, 13 Jun 2026 07:02:30 GMT
• Title: RepWAM: World Action Modeling with Representation Visual-Action Tokenizers
• Abstract summary: RepWAM is a representation-centric world action model built on representation visual-action tokenizers.<n>We train a representation visual-action tokenizer that maps visual inputs into aligned visual and latent action tokens.<n>We then pretrain our WAM to jointly model future visual states and the latent actions that connect them under language instructions.
• Score: 120.87642891397853
• License: http://creativecommons.org/licenses/by/4.0/
• 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, we explore a semantic visual-action latent space for representation-centric world action modeling. Specifically, we train a representation visual-action tokenizer that maps visual inputs into aligned visual and latent action tokens. We then pretrain our WAM to jointly model future visual states and the latent actions that connect them under language instructions, followed by adaptation to real robot trajectories for closed-loop manipulation. Experiments on real-world manipulation tasks and simulation benchmarks show that RepWAM delivers strong performance across diverse manipulation settings, while ablations highlight the value of semantic visual-action tokenization over 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. Code and weights will be available at https://github.com/wdrink/RepWAM.

Related papers

• Masked Visual Actions for Unified World Modeling [96.12988421978463]
  We introduce Masked Visual Actions, a pixel-space control interface that expresses action as a partially revealed trajectory of an arbitrary entity in a video.<n>Revealing robot motion makes the model act as a forward dynamics model that predicts the scene's response to low-level robot actions, while revealing desired object motion makes the same model recover robot behavior consistent with that outcome.
  arXiv  Detail & Related papers  (2026-07-21T17:59:11Z)
• World Action Models: A Survey [100.95337034529263]
  World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action.<n>Recent WAMs repurpose large video generation models, and a parallel line relies on language or vision-language backbones without a video-generation core.<n>This survey gives the field a common account. It first clarifies these boundaries, then organizes existing works through two complementary views.
  arXiv  Detail & Related papers  (2026-06-18T17:05:19Z)
• From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data [71.22409934108924]
  Human videos are abundant and capture rich interactions, providing diverse semantic and physical cues for real-world manipulation.<n>This survey provides a unified view of how human videos are transformed into effective knowledge for Vision-Language-Action (VLA) models.<n>We highlight three key open challenges in this area: structuring unstructured videos into training-ready episodes, grounding video-derived supervision into robot-executable actions under embodiment and viewpoint heterogeneity, and designing evaluation protocols that better predict real-world deployment performance and transfer efficiency.
  arXiv  Detail & Related papers  (2026-05-18T06:19:16Z)
• DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation [52.136378691610524]
  We present DynaRend, a representation learning framework that learns 3D-aware and dynamics-informed triplane features.<n>By pretraining on multi-view RGB-D video data, DynaRend jointly captures spatial geometry, future dynamics, and task semantics in a unified triplane representation.<n>We evaluate DynaRend on two challenging benchmarks, RLBench and Colosseum, demonstrating substantial improvements in policy success rate, generalization to environmental perturbations, and real-world applicability across diverse manipulation tasks.
  arXiv  Detail & Related papers  (2025-10-28T10:17:11Z)
• Latent Action Pretraining Through World Modeling [1.988007188564225]
  We propose LAWM, a model-agnostic framework to pretrain imitation learning models in a self-supervised way.<n>Our framework is designed to be effective for transferring across tasks, environments, and embodiments.
  arXiv  Detail & Related papers  (2025-09-22T21:19:10Z)
• Precise Action-to-Video Generation Through Visual Action Prompts [62.951609704196485]
  Action-driven video generation faces a precision-generality trade-off.<n>Agent-centric action signals provide precision at the cost of cross-domain transferability.<n>We "render" actions into precise visual prompts as domain-agnostic representations.
  arXiv  Detail & Related papers  (2025-08-18T17:12:28Z)
• ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver [35.25196177784228]
  We propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm.<n>Conditioned on the model's visual outputs, a diffusion transformer reconstructs the gaze region of the image.<n>This process prompts the VLA model to learn fine-grained representations and accurately allocate visual attention.
  arXiv  Detail & Related papers  (2025-08-14T04:20:19Z)
• Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics [11.88216611522207]
  We show that off-the-shelf text-based Transformers, with no additional training, can perform few-shot in-context visual imitation learning. We achieve this by transforming visual observations into sequences of tokens that a text-pretrained Transformer can ingest and generate. Despite being trained only on language, we show that these Transformers excel at translating tokenised visual keypoint observations into action trajectories.
  arXiv  Detail & Related papers  (2024-03-28T17:04:00Z)
• Masked World Models for Visual Control [90.13638482124567]
  We introduce a visual model-based RL framework that decouples visual representation learning and dynamics learning. We demonstrate that our approach achieves state-of-the-art performance on a variety of visual robotic tasks.
  arXiv  Detail & Related papers  (2022-06-28T18:42:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.