# UniMoFlow: Grounding Instruction-Driven 3D Human Motion Editing in Generation

arXiv: https://arxiv.org/abs/2608.09143 · HTML: https://mlsanity.com/paper/2608.09143/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 23 of 23)

- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [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)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models](https://mlsanity.com/paper/2412.08629/) (2024)
- [Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression](https://mlsanity.com/paper/2411.16575/) (2024)
- [ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer](https://mlsanity.com/paper/2410.00086/) (2024)
- [StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework](https://mlsanity.com/paper/2405.05691/) (2024)
- [SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing](https://mlsanity.com/paper/2503.13836/) (2025)
- [DreamOmni: Unified Image Generation and Editing](https://mlsanity.com/paper/2412.17098/) (2024)
- [MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm](https://mlsanity.com/paper/2502.02358/) (2025)
- [SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction](https://mlsanity.com/paper/2503.18211/) (2025)
- [Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing](https://mlsanity.com/paper/2410.18977/) (2024)
- [Dynamic Motion Blending for Versatile Motion Editing](https://mlsanity.com/paper/2503.20724/) (2025)
- [PartMotionEdit: Fine-Grained Text-Driven 3D Human Motion Editing via Part-Level Modulation](https://mlsanity.com/paper/2512.24200/) (2025)
- [Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning](https://mlsanity.com/paper/2605.30969/) (2026)
- [A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting](https://mlsanity.com/paper/2604.13427/) (2026)

## Abstract (arXiv)

Instruction-driven editing of 3D human motion requires precise spatiotemporal localization, rich semantic grounding, and strict preservation of unmodified content. Existing methods either resort to training-free adaptation of generative models or rely solely on triplet supervision; however, adaptation often yields suboptimal control, and manually curated triplet datasets remain severely limited in scale and semantic diversity. To overcome this bottleneck, we ground motion editing directly within text-to-motion generation across data, architecture, and inference. At the data level, we develop a closed-loop synthesis-and-verification pipeline that produces Omni-MoEdit, a large-scale dataset spanning body-part, amplitude, temporal, action, and style edits. At the architectural level, we introduce UniMoFlow, a unified latent flow-matching model that shares broad semantic and kinematic knowledge between generation and editing. At the inference level, SAFE (Source-Anchored Flow Editing) complements UniMoFlow with controllable, source-anchored refinement. Furthermore, we augment standard evaluations with semantics-aware metrics to account for valid edits that inherently deviate from a single ground-truth reference. Extensive experiments demonstrate improved target-text alignment, edit effectiveness, and cycle consistency, while maintaining competitive source fidelity and text-to-motion generation quality.