# Copper-Policy: Focus on the Representation for Robust Robot Manipulation

arXiv: https://arxiv.org/abs/2609.32779 · HTML: https://mlsanity.com/paper/2609.32779/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 27 of its 54 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 27 of 27)

- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [Causal World Modeling for Robot Control](https://mlsanity.com/paper/2601.21998/) (2026)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026)
- [GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation](https://mlsanity.com/paper/2410.06158/) (2024)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model](https://mlsanity.com/paper/2510.12276/) (2025)
- [ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning](https://mlsanity.com/paper/2602.11236/) (2026)
- [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://mlsanity.com/paper/2605.00078/) (2026)
- [Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising](https://mlsanity.com/paper/2604.26694/) (2026)
- [Training-Time Action Conditioning for Efficient Real-Time Chunking](https://mlsanity.com/paper/2512.05964/) (2025)
- [AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing](https://mlsanity.com/paper/2606.09811/) (2026)
- [Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution](https://mlsanity.com/paper/2602.12684/) (2026)
- [World Guidance: World Modeling in Condition Space for Action Generation](https://mlsanity.com/paper/2602.22010/) (2026)
- [Do World Action Models Generalize Better than VLAs? A Robustness Study](https://mlsanity.com/paper/2603.22078/) (2026)
- [StarVLA-α: Reducing Complexity in Vision-Language-Action Systems](https://mlsanity.com/paper/2604.11757/) (2026)
- [EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies](https://mlsanity.com/paper/2606.20092/) (2026)
- [G0.5: One Autoregressive Stream for Robot Reasoning and Action](https://mlsanity.com/paper/2608.11739/) (2026)
- [Learning 4D Geometric Priors for Inference-Efficient World Action Models](https://mlsanity.com/paper/2607.05468/) (2026)
- [JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling](https://mlsanity.com/paper/2608.09381/) (2026)
- [LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation](https://mlsanity.com/paper/2608.03701/) (2026)
- [RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation](https://mlsanity.com/paper/2607.06559/) (2026)
- [StageWAM: Joint-Embedding Stage Prediction for World-Action Models in Robot Manipulation](https://mlsanity.com/paper/2608.10780/) (2026)

## Abstract (arXiv)

World Action Models (WAMs) acquire behavioral priors by modeling future scene evolution, but predicting detailed futures in pixel or latent space incurs substantial cost. Recent evidence that co-training gains persist without test-time generation raises a question: what must a WAM learn to improve control? We introduce Copper-Policy, which learns a compact World representation with the policy rather than relying on a predefined target space. Through temporal joint-embedding prediction, it predicts future observation embeddings conditioned on task intention without reconstructing pixels. This prediction and action decoding shape the representation jointly, while the policy retains access to current-frame spatial detail for execution. Representation analyses show that the learned features better separate task-driven change from perturbations and provide complementary information for control. Compact prediction targets reduce training tokens per sample, enabling a 2B-parameter model trained in 9.67 hours on 8× RTX 5090 GPUs and 6× faster than Fast-WAM on matched A100 GPUs. Copper-Policy outperforms every compared method without embodied pretraining on RoboTwin and several embodied-pretrained VLAs on LIBERO-Plus (80.85%). On three challenging real-robot tasks, it performs comparably to π0.5 and attains a higher average score. Together, these results show that Copper-Policy combines strong control performance with efficient training.