# ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning

Source: [ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning](<https://www.sota2.com/research/paper/69b8e00e0636e5bf4afbea68>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-18T05:00:04.467Z

Authors: Eric Nazarenus, Chuqiao Li, Yannan He, Xianghui Xie, Jan Eric Lenssen, Gerard Pons-Moll

Published: 2026-03-13T18:24:32.000Z

## Abstract

We present ActionPlan, a unified motion diffusion framework that bridges real-time streaming with high-quality offline generation within a single model. The core idea is to introduce a per-frame action plan: the model predicts frame-level text latents that act as dense semantic anchors throughout denoising, and uses them to denoise the full motion sequence with combined semantic and motion cues. To support this structured workflow, we design latent-specific diffusion steps, allowing each motion latent to be denoised independently and sampled in flexible orders at inference. As a result, ActionPlan can run in a history-conditioned, future-aware mode for real-time streaming, while also supporting high-quality offline generation. The same mechanism further enables zero-shot motion editing and in-betweening without additional models. Experiments demonstrate that our real-time streaming is 5.25x faster while also achieving 18% motion quality improvement over the best previous method in terms of FID.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Text-to-Motion Generation on HumanML3D-272 (test)](<https://www.sota2.com/research/sota/text-to-motion-generation-on-humanml3d-272-test.md>): Text-to-motion generation; HumanML3D-272 (test); FID: 5.522.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.13500>)

[PDF](<https://arxiv.org/pdf/2603.13500.pdf>)
