ActionSplice: In-Flight Action Editing for Interactive World Models
Summary
ActionSplice introduces counterfactual state transport to splice revised actions into chunk-autoregressive video world models without replaying completed evaluations, improving fidelity and inference speed.
View Cached Full Text
Cached at: 09/14/26, 02:35 PM
Paper page - ActionSplice: In-Flight Action Editing for Interactive World Models
Source: https://huggingface.co/papers/2609.08230 Published on Sep 8
·
Submitted byhttps://huggingface.co/PardisTaghavi
pardison Sep 14
Abstract
ActionSplice introduces counterfactual state transport to splice revised actions into chunk-autoregressive video world models without replaying completed evaluations, improving fidelity and speed.
Chunk-autoregressive video world modelstypically condition each generated chunk on one action. An action received during sampling must therefore wait for the next chunk, condition future solver evaluations on a state produced under the previous action, or trigger rollback that repeats completed evaluations. We introduceActionSplice, an inference framework that formulates this problem asCounterfactual State Transport(CST). A lightweightcorrectortransports the interruptedbackbone-native representationtoward the matched 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. The retargeting variant CST*{R} updates the entire active chunk, while the temporal-splicing variant CST*{T} preserves a temporal prefix and updates only the suffix. Across minWM-Wan Action2V and HY-WM1.5, CST*{R} reduces rollback-relativeLPIPSby 61.5% and 75.9% relative to direct condition swapping. CST*{T} reduces suffixLPIPSby 56.1% and 77.5%, respectively, while providing 2.73times and 1.69times pixel-ready speedups over waiting. Under the HY-WorldPlay protocol, CST_{R} obtains aPSNRof 25.66 dB, anSSIMof 0.6902, and anLPIPSof 0.1337 against the original rollout.
View arXiv pageView PDFProject pageGitHub3Add to collection
Get this paper in your agent:
hf papers read 2609\.08230
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2609.08230 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2609.08230 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2609.08230 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
ActWorld: From Explorable to Interactive World Model via Action-Aware Memory
ActWorld proposes a chunk-autoregressive world model with hierarchical action-aware memory to support object interaction alongside navigation, addressing data and memory bottlenecks in existing interactive world models.
Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
Light-WAM is a lightweight world action model for efficient robot manipulation that uses a compact video backbone and downsampled latent space for future-video supervision, achieving high performance with low inference latency.
Flash-WAM: Modality-Aware Distillation for World Action Models
Flash-WAM introduces a modality-aware distillation method for world-action models, achieving real-time inference by compressing diffusion to a single step per modality, resulting in 23x speedup.
GameWAM: A World Action Model for Video Games
GameWAM introduces the first unified world-action model for native video-game control, jointly predicting future visuals and executable actions using block-causal flow matching and mode-specific distributions.
World Pilot: Steering Vision-Language-Action Models with World-Action Priors
World Pilot enhances Vision-Language-Action models by incorporating dynamic scene evolution and trajectory priors from a World-Action Model, achieving state-of-the-art zero-shot performance on manipulation tasks.