# ActiveWAM: Evidence-Aware Active Vision for World-Action Models

arXiv: https://arxiv.org/abs/2610.01698 · HTML: https://mlsanity.com/paper/2610.01698/

## 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 7 of its 34 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Placed in

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

## Builds on (most cited first, 7 of 7)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control](https://mlsanity.com/paper/2603.10448/) (2026)
- [Optimizing Active Perception for Learning Simultaneous Viewpoint Selection and Manipulation with Diffusion Policy](https://mlsanity.com/paper/2409.14615/) (2024)
- [TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learning](https://mlsanity.com/paper/2605.07943/) (2026)
- [Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation](https://mlsanity.com/paper/2606.23625/) (2026)

## Abstract (arXiv)

Active vision manipulation requires a policy to control both its camera and its end-effectors, yet camera motion determines which evidence remains visible within finite observation windows. Acquiring a new view can displace task-critical cues, while retaining a view forgoes potentially useful observations. We formulate this as an evidence-aware retain--acquire problem and present ActiveWAM, a unified world--action model that learns observation and manipulation jointly. To this end, we propose training-time inversion which constrains a frozen video prior by task-bearing source evidence and visible temporal changes, eliminating the need for test-time inversion or candidate ranking. At deployment, the policy generates bimanual and pan/tilt actions-including stay and reacquisition behaviors-from view-aware history, and updates context from newly measured RGB observations. Future-video prediction serves as a co-training signal, while action generation requires neither future-video decoding nor optimal viewpoint annotations. We introduce RoboTwin-AV, a 50-task benchmark with executable pan/tilt control and automatically generated demonstrations. ActiveWAM improves TAVIS out-of-distribution success by up to 17.0 percentage points over the strongest baselines, achieves 20.0 additional points over Fast-WAM on RoboTwin-AV, and outperforms it by 26.7 points on real-world physical kitchen tasks.