# Per-Stroke Temporal Control for Text-to-Motion via Action Units and Action-Detection Guidance

arXiv: https://arxiv.org/abs/2607.15717 · HTML: https://mlsanity.com/paper/2607.15717/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 42 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Builds on (most cited first, 30 of 39)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model](https://mlsanity.com/paper/2303.09833/) (2023)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [BABEL: Bodies, Action and Behavior with English Labels](https://mlsanity.com/paper/2106.09696/) (2021)
- [OmniControl: Control Any Joint at Any Time for Human Motion Generation](https://mlsanity.com/paper/2310.08580/) (2023)
- [MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis](https://mlsanity.com/paper/2212.04495/) (2022)
- [FLAME: Free-form Language-based Motion Synthesis & Editing](https://mlsanity.com/paper/2209.00349/) (2022)
- [TEACH: Temporal Action Composition for 3D Humans](https://mlsanity.com/paper/2209.04066/) (2022)
- [InstanceDiffusion: Instance-level Control for Image Generation](https://mlsanity.com/paper/2402.03290/) (2024)
- [ASFormer: Transformer for Action Segmentation](https://mlsanity.com/paper/2110.08568/) (2021)
- [MMM: Generative Masked Motion Model](https://mlsanity.com/paper/2312.03596/) (2023)
- [AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism](https://mlsanity.com/paper/2309.00796/) (2023)
- [FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing](https://mlsanity.com/paper/2312.15004/) (2023)
- [Human Motion Generation: A Survey](https://mlsanity.com/paper/2307.10894/) (2023)
- [Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation](https://mlsanity.com/paper/2401.08559/) (2024)
- [DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control](https://mlsanity.com/paper/2410.05260/) (2024)
- [Flexible Motion In-betweening with Diffusion Models](https://mlsanity.com/paper/2405.11126/) (2024)

## Abstract (arXiv)

Text-to-motion models are competent at the action a prompt names but unreliable at when each stroke lands: four punches alternating left and right rarely return four separable strokes. We introduce typed temporal events called Action Units (AUs) that make the individual stroke -- its body track, action class, time window, and impact timing -- an explicit conditioning signal. We ground a frozen text-to-motion backbone on the AU set through a lightweight gated adapter injecting two streams (per-stroke tokens and a per-frame phase channel), and at inference close residual timing errors with a training-free classifier gradient from a frozen frame-level detector. We measure per-stroke control on StrokeBench, whose prompts specify count, ordering, track, and core-frame placement, paired with an audited stroke corpus. AU grounding markedly raises the rate of correctly placed single strokes over the strongest prior interface, at the best motion quality among text-, interval-, and frame-level baselines. The prompted core frame emerges as a further steerable axis.