# ActionSplice: In-Flight Action Editing for Interactive World Models

arXiv: https://arxiv.org/abs/2609.08230 · HTML: https://mlsanity.com/paper/2609.08230/

## 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 24 of its 38 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [CameraCtrl: Enabling Camera Control for Text-to-Video Generation](https://mlsanity.com/paper/2404.02101/) (2024)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity](https://mlsanity.com/paper/2502.01776/) (2025)
- [Matrix-game 2.0: An open-source real-time and streaming interactive world model](https://mlsanity.com/paper/2508.13009/) (2025)
- [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://mlsanity.com/paper/2602.02214/) (2026)
- [WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling](https://mlsanity.com/paper/2512.14614/) (2025)
- [Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory](https://mlsanity.com/paper/2604.08995/) (2026)
- [LongCat-Video Technical Report](https://mlsanity.com/paper/2510.22200/) (2025)
- [Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation](https://mlsanity.com/paper/2605.15141/) (2026)
- [Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models](https://mlsanity.com/paper/2606.25473/) (2026)
- [minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models](https://mlsanity.com/paper/2605.30263/) (2026)
- [Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion](https://mlsanity.com/paper/2603.13405/) (2026)
- [Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation](https://mlsanity.com/paper/2605.16003/) (2026)
- [C3ache: Accelerating World Action Models with Cross Inference Chunk Cache](https://mlsanity.com/paper/2606.08962/) (2026)
- [X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference](https://mlsanity.com/paper/2604.20289/) (2026)
- [BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression](https://mlsanity.com/paper/2606.10135/) (2026)
- [Diffusion ReRoll: Revisable Denoising for Robotic Sequential Prediction](https://mlsanity.com/paper/2607.19919/) (2026)
- [NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Driving](https://mlsanity.com/paper/2603.07901/) (2026)
- [Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse](https://mlsanity.com/paper/2604.04451/) (2026)
- [Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models](https://mlsanity.com/paper/2605.31158/) (2026)
- [Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation](https://mlsanity.com/paper/2605.14382/) (2026)
- [Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation](https://mlsanity.com/paper/2607.26694/) (2026)
- [Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models](https://mlsanity.com/paper/2608.18484/) (2026)

## Abstract (arXiv)

Chunk-autoregressive video world models typically generate each chunk under one action. When an action changes during sampling, waiting until the next chunk delays the response, while directly switching the conditioning leaves the intermediate solver state shaped by the previous action. Restarting sampling under the revised action avoids this mismatch but repeats completed computation. We introduce ActionSplice, which edits the interrupted state through Counterfactual State Transport (CST). A lightweight corrector moves the interrupted solver state toward the matched counterfactual solver state induced by the revised action at the same solver step. The world model and sampler remain frozen, and sampling resumes without replaying completed evaluations. CSTR retargets the entire active chunk, while CSTT preserves the temporal prefix at the intervention step and corrects only the suffix. On minWM--Wan Action2V and HY-WM1.5, we measure fidelity against matched rollback references. Relative to condition swapping, CSTR reduces LPIPS by 61.5% and 75.9%, and CSTT reduces suffix LPIPS by 56.1% and 77.5%, respectively.