# Flex-π: A Multi-Stream World-Action Model with Compute Flexibility

arXiv: https://arxiv.org/abs/2608.10860 · HTML: https://mlsanity.com/paper/2608.10860/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 53 of its 99 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

## Builds on (most cited first, 30 of 53)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [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)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (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)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [Causal World Modeling for Robot Control](https://mlsanity.com/paper/2601.21998/) (2026)
- [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://mlsanity.com/paper/2510.10274/) (2025)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [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)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [MolmoAct: Action Reasoning Models that can Reason in Space](https://mlsanity.com/paper/2508.07917/) (2025)
- [RoboDreamer: Learning Compositional World Models for Robot Imagination](https://mlsanity.com/paper/2404.12377/) (2024)
- [DreamGen: Unlocking Generalization in Robot Learning through Video World Models](https://mlsanity.com/paper/2505.12705/) (2025)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [GigaWorld-Policy: An Efficient Action-Centered World--Action Model](https://mlsanity.com/paper/2603.17240/) (2026)
- [Interactive Post-Training for Vision-Language-Action Models](https://mlsanity.com/paper/2505.17016/) (2025)

## Built on by (most cited first, 11 of 11)

- [GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulation](https://mlsanity.com/paper/2609.04193/) (2026)
- [GlanceWAM: Sparse Test-Time Imagination for World-Action Models](https://mlsanity.com/paper/2608.23927/) (2026)
- [Modality-Autoregressive World-Action Models](https://mlsanity.com/paper/2609.17524/) (2026)
- [PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics](https://mlsanity.com/paper/2609.19142/) (2026)
- [Grounded Action Model: 3D Grounding as a Foundation for Robotics](https://mlsanity.com/paper/2609.23863/) (2026)
- [From World Models to World Action Models: Rethinking Next-State Prediction](https://mlsanity.com/paper/2609.34414/) (2026)
- [One from Infinity: Actualizing Futures from Pretrained World Models into Robot Actions](https://mlsanity.com/paper/2609.36413/) (2026)
- [PreferenceFlow: Test-Time Guidance of Flow-Matching Robot Policies from Human Interventions](https://mlsanity.com/paper/2609.36872/) (2026)
- [WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models](https://mlsanity.com/paper/2610.11401/) (2026)
- [What Visual Representations Do World Action Models Need?](https://mlsanity.com/paper/2610.13024/) (2026)
- [RAIN: Robotic Task Generalization with Region-Aware Interaction Networks](https://mlsanity.com/paper/2610.14039/) (2026)

## Abstract (arXiv)

World-action models (WAMs) predict the future to act better, but nearly all of them predict only RGB latents, trained purely for pixel reconstruction, with no explicit signal for the 3D geometry or object semantics manipulation needs. We find a surprising free lunch: the same frozen video-generation VAE that encodes RGB also encodes 3D pointmaps almost losslessly, with no pointmap-specific training at all. This lets us supervise Flex-π, a 6B-parameter WAM, on 3D geometry and object-centric DINO semantics alongside RGB, at no cost in new sensors, new pre-training, or inference latency. Every visual signal is projected into this shared latent space and denoised jointly with actions inside a Mixture-of-Transformers backbone; per-stream dropout with cross-modality forcing then lets a single trained checkpoint run on any subset of these streams, from a fast action-only mode to full joint generation. The result is a policy that is exceptionally demonstration-efficient and generalizes well, beating the strongest baselines by up to 2-7× on dexterous, precise, real-world bimanual manipulation tasks both in and out of distribution, all while running faster than π0.5. Our project website: https://flex-pi.github.io/