# SANTS: A State-Adaptive Scheduler for World Action Models

arXiv: https://arxiv.org/abs/2605.27947 · HTML: https://mlsanity.com/paper/2605.27947/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 33 of its 41 references that are in the map.
- First posted on arXiv 27 May 2026.

## Placed in

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

## Builds on (most cited first, 30 of 33)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [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)
- [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025)
- [Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation](https://mlsanity.com/paper/2312.13139/) (2023)
- [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)
- [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)
- [Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations](https://mlsanity.com/paper/2412.14803/) (2024)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics](https://mlsanity.com/paper/2310.13268/) (2023)
- [mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs](https://mlsanity.com/paper/2512.15692/) (2025)
- [GigaWorld-Policy: An Efficient Action-Centered World--Action Model](https://mlsanity.com/paper/2603.17240/) (2026)
- [Align Your Steps: Optimizing Sampling Schedules in Diffusion Models](https://mlsanity.com/paper/2404.14507/) (2024)
- [DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control](https://mlsanity.com/paper/2603.10448/) (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)
- [WorldEval: World Model as Real-World Robot Policies Evaluator](https://mlsanity.com/paper/2505.19017/) (2025)
- [Motubrain: An Advanced World Action Model for Robot Control](https://mlsanity.com/paper/2604.27792/) (2026)
- [World Action Models: The Next Frontier in Embodied AI](https://mlsanity.com/paper/2605.12090/) (2026)
- [VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation](https://mlsanity.com/paper/2411.09153/) (2024)
- [RISE: Self-Improving Robot Policy with Compositional World Model](https://mlsanity.com/paper/2602.11075/) (2026)
- [World Guidance: World Modeling in Condition Space for Action Generation](https://mlsanity.com/paper/2602.22010/) (2026)
- [OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation](https://mlsanity.com/paper/2605.06481/) (2026)
- [ViPRA: Video Prediction for Robot Actions](https://mlsanity.com/paper/2511.07732/) (2025)
- [Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling](https://mlsanity.com/paper/2512.03044/) (2025)
- [D3P: Dynamic Denoising Diffusion Policy via Reinforcement Learning](https://mlsanity.com/paper/2508.06804/) (2025)
- [HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models](https://mlsanity.com/paper/2605.10942/) (2026)

## Built on by (most cited first, 7 of 7)

- [World Action Models: A Survey](https://mlsanity.com/paper/2606.20781/) (2026)
- [Test-Time Scaling for World Action Models via Zero-Shot Geometric Evaluation](https://mlsanity.com/paper/2607.17454/) (2026)
- [World-Action Models for Robot Learning and Control: A Survey](https://mlsanity.com/paper/2609.16074/) (2026)
- [Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade](https://mlsanity.com/paper/2608.14650/) (2026)
- [ReSync: Re-Aligning the Two Clocks of Asynchronous World-Action Models](https://mlsanity.com/paper/2609.33944/) (2026)
- [Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks](https://mlsanity.com/paper/2609.36471/) (2026)
- [WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models](https://mlsanity.com/paper/2610.11401/) (2026)

## Abstract (arXiv)

World Action Models (WAMs) improve robot manipulation by using video-based future representations to condition action generation. In pixel-space WAMs, however, the best action condition is not necessarily the fully denoised video. Controlled denoising-depth scans show that video refinement can reduce action error up to a state-dependent point, after which the gain may saturate or even reverse when late predictions become less action-relevant or physically unreliable. This suggests that action generation should use a state-dependent point along the video noise trajectory rather than a fixed terminal denoising depth. We introduce State-Adaptive Noise Trajectory Scheduler (SANTS), a lightweight scheduler for video-to-action diffusion policies. At each video decision point, SANTS reads the current video-state representation and noise level, then jointly predicts a cumulative stopping hazard and a relative noise-progression ratio. SANTS is post-trained with a path-level reward computed after the frozen action branch generates the final action chunk, so the scheduler is optimized for downstream action quality rather than intermediate video fidelity, while redundant video-state updates are explicitly penalized. Experiments show that SANTS reaches (94.4%) overall success on RoboTwin 2.0 and (73.1%) average success across seven real-robot tasks, while reducing latency by (81.7%) and (79.0%) relative to full video denoising, respectively. These results indicate that adaptive selection along the video noise trajectory can preserve the control benefits of WAM-style future reasoning while removing much of its redundant inference cost.