# Scaling World Model for Hierarchical Manipulation Policies

arXiv: https://arxiv.org/abs/2602.10983 · HTML: https://mlsanity.com/paper/2602.10983/

## Key facts

- Cited by 16 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 16 of its 52 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)
- Vision-language-action models / [Generalist VLA models and benchmarks](https://mlsanity.com/vla/generalist-vla-models-and-benchmarks/)

## Builds on (most cited first, 16 of 16)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [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)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025)
- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024)
- [Galaxea Open-World Dataset and G0 Dual-System VLA Model](https://mlsanity.com/paper/2509.00576/) (2025)
- [What Matters in Building Vision-Language-Action Models for Generalist Robots](https://mlsanity.com/paper/2412.14058/) (2024)
- [WoW: Towards a World omniscient World model Through Embodied Interaction](https://mlsanity.com/paper/2509.22642/) (2025)
- [Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting](https://mlsanity.com/paper/2509.22195/) (2025)
- [VLA-R1: Enhancing Reasoning in Vision-Language-Action Models](https://mlsanity.com/paper/2510.01623/) (2025)
- [Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representations](https://mlsanity.com/paper/2509.11417/) (2025)
- [TeViR: Text-to-Video Reward with Diffusion Models for Efficient Reinforcement Learning](https://mlsanity.com/paper/2505.19769/) (2025)

## Built on by (most cited first, 16 of 16)

- [Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising](https://mlsanity.com/paper/2604.26694/) (2026)
- [MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models](https://mlsanity.com/paper/2606.09827/) (2026)
- [τ0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation](https://mlsanity.com/paper/2608.16885/) (2026)
- [Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model](https://mlsanity.com/paper/2607.11643/) (2026)
- [SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space](https://mlsanity.com/paper/2608.01397/) (2026)
- [World Pilot: Steering Vision-Language-Action Models with World-Action Priors](https://mlsanity.com/paper/2606.12403/) (2026)
- [StageWAM: Joint-Embedding Stage Prediction for World-Action Models in Robot Manipulation](https://mlsanity.com/paper/2608.10780/) (2026)
- [2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation](https://mlsanity.com/paper/2609.11308/) (2026)
- [Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation](https://mlsanity.com/paper/2603.12553/) (2026)
- [See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs](https://mlsanity.com/paper/2606.02735/) (2026)
- [Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems](https://mlsanity.com/paper/2606.00090/) (2026)
- [Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation](https://mlsanity.com/paper/2608.05999/) (2026)
- [H-VLA: Hierarchical Vision-Language-Action Model with Key-Action Reasoning and Motion Planning in a Unified Action Space](https://mlsanity.com/paper/2609.22895/) (2026)
- [SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models](https://mlsanity.com/paper/2609.33575/) (2026)
- [EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Action](https://mlsanity.com/paper/2609.39973/) (2026)
- [World Action Modeling with Progressive Visual Planning](https://mlsanity.com/paper/2610.02508/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models are promising for generalist robot manipulation but remain brittle in out-of-distribution (OOD) settings, especially with limited real-robot data. To resolve the generalization bottleneck, we introduce a hierarchical Vision-Language-Action framework our that leverages the generalization of large-scale pre-trained world model for robust and generalizable VIsual Subgoal TAsk decomposition VISTA. Our hierarchical framework our consists of a world model as the high-level planner and a VLA as the low-level executor. The high-level world model first divides manipulation tasks into subtask sequences with goal images, and the low-level policy follows the textual and visual guidance to generate action sequences. Compared to raw textual goal specification, these synthesized goal images provide visually and physically grounded details for low-level policies, making it feasible to generalize across unseen objects and novel scenarios. We validate both visual goal synthesis and our hierarchical VLA policies in massive out-of-distribution scenarios, and the performance of the same-structured VLA in novel scenarios could boost from 14% to 69% with the guidance generated by the world model. Results demonstrate that our method outperforms previous baselines with a clear margin, particularly in out-of-distribution scenarios. Project page: hrefhttps://vista-wm.github.io/https://vista-wm.github.io