# Flash-WAM: Modality-Aware Distillation for World Action Models

arXiv: https://arxiv.org/abs/2606.05254 · HTML: https://mlsanity.com/paper/2606.05254/

## Key facts

- Cited by 19 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 41 of its 41 references that are in the map.
- First posted on arXiv 3 Jun 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 41)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (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)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [One Step Diffusion via Shortcut Models](https://mlsanity.com/paper/2410.12557/) (2024)
- [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)
- [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://mlsanity.com/paper/2510.10274/) (2025)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [Real-Time Execution of Action Chunking Flow Policies](https://mlsanity.com/paper/2506.07339/) (2025)
- [Consistency Models Made Easy](https://mlsanity.com/paper/2406.14548/) (2024)
- [GigaWorld-Policy: An Efficient Action-Centered World--Action Model](https://mlsanity.com/paper/2603.17240/) (2026)
- [VideoLCM: Video Latent Consistency Model](https://mlsanity.com/paper/2312.09109/) (2023)
- [Video Generators are Robot Policies](https://mlsanity.com/paper/2508.00795/) (2025)
- [DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping](https://mlsanity.com/paper/2502.20900/) (2025)
- [One-Step Diffusion Distillation through Score Implicit Matching](https://mlsanity.com/paper/2410.16794/) (2024)
- [Progressive Distillation for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2202.00512/) (2022)
- [A Comprehensive Survey on World Models for Embodied AI](https://mlsanity.com/paper/2510.16732/) (2025)
- [T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design](https://mlsanity.com/paper/2410.05677/) (2024)
- [World Model for Robot Learning: A Comprehensive Survey](https://mlsanity.com/paper/2605.00080/) (2026)

## Built on by (most cited first, 19 of 19)

- [A Definition and Roadmap for World Models](https://mlsanity.com/paper/2607.06401/) (2026)
- [WAM-OPD: On-Policy Distillation for World Action Models](https://mlsanity.com/paper/2608.22364/) (2026)
- [GlanceWAM: Sparse Test-Time Imagination for World-Action Models](https://mlsanity.com/paper/2608.23927/) (2026)
- [N0-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation](https://mlsanity.com/paper/2607.23783/) (2026)
- [WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model](https://mlsanity.com/paper/2608.01845/) (2026)
- [DIDO: Distilling Interaction-Centric Dynamics into One-Step Denoising for World Action Models](https://mlsanity.com/paper/2609.15570/) (2026)
- [DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation](https://mlsanity.com/paper/2608.22067/) (2026)
- [Streaming-WAM: Action-Conditioned World-Action Model for Asynchronous Robot Manipulation](https://mlsanity.com/paper/2609.28927/) (2026)
- [Rolling-WAM: World Action Models with Rolling Imagination](https://mlsanity.com/paper/2609.30247/) (2026)
- [MoWAM: Explicit Future Motion Prediction for Efficient World Action Models](https://mlsanity.com/paper/2609.20709/) (2026)
- [An Action Is Worth One Patch: Unified World-Action Modeling with PatchWAM](https://mlsanity.com/paper/2609.25961/) (2026)
- [Dynamic Manipulation with World-Action Models via Counterfactual Planning](https://mlsanity.com/paper/2609.33172/) (2026)
- [Q-WAM: 4-Bit Quantization of World Action Models with Action-Subspace Protection](https://mlsanity.com/paper/2609.33269/) (2026)
- [AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models](https://mlsanity.com/paper/2609.33748/) (2026)
- [WAM-OPD: Sharpening World Action Models via On-Policy Distillation](https://mlsanity.com/paper/2609.34250/) (2026)
- [RealtimeWAM: One-Step Asynchronous World Action Models](https://mlsanity.com/paper/2610.06617/) (2026)
- [WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models](https://mlsanity.com/paper/2610.11401/) (2026)
- [1Step-WAM: Your World Action Model but Faster using 1-Step Action Generation](https://mlsanity.com/paper/2610.15625/) (2026)
- [MARS: Systematic Multi-Level Acceleration for World Action Models](https://mlsanity.com/paper/2610.17141/) (2026)

## Abstract (arXiv)

World-action models (WAMs) jointly generate future video and robot actions through iterative diffusion, achieving strong performance on manipulation benchmarks but requiring tens of denoising steps, a cost that precludes real-time control. Step distillation has emerged as the natural remedy, but off-the-shelf methods break down in the joint video-action setting because video and action streams use different SNR-shifted noise schedules and reach training with substantially different marginal noise distributions, an asymmetry that single-modality distillation methods cannot accommodate. We introduce Flash-WAM, a modality-aware step-distillation framework inspired by consistency distillation that selects the consistency function for each modality to match its noise regime: a linear-gradient-scaling parametrization for the action stream's low-noise regime, paired with a variance-preserving parametrization for the video stream's high-noise regime, grounded in a structural analysis of the consistency-function family that characterizes the achievable gradient scaling under the consistency boundary condition. Instantiated on LingBot-VA, Flash-WAM compresses inference to a single step in each modality. On RoboTwin 2.0, this reduces per-chunk latency from 8.1 seconds to 348 ms on NVIDIA L40S, a 23× speedup that enables real-time inference. Flash-WAM preserves task success on simulation benchmarks (85.5% RoboTwin 2.0, 95.7% LIBERO) and substantially recovers real-world performance (60% average on a Unitree G1 humanoid robot), while naive consistency distillation drops to 24% at the same step budget.