# SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing

arXiv: https://arxiv.org/abs/2503.13836 · HTML: https://mlsanity.com/paper/2503.13836/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 53 of its 59 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing](https://mlsanity.com/paper/2304.08465/) (2023)
- [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)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://mlsanity.com/paper/2303.09535/) (2023)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)

## Built on by (most cited first, 30 of 39)

- [Causal Motion Diffusion Models for Autoregressive Motion Generation](https://mlsanity.com/paper/2602.22594/) (2026)
- [ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model](https://mlsanity.com/paper/2506.02452/) (2025)
- [Text-driven Motion Generation: Overview, Challenges and Directions](https://mlsanity.com/paper/2505.09379/) (2025)
- [IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation](https://mlsanity.com/paper/2512.10730/) (2025)
- [X-MoGen: Unified Motion Generation across Humans and Animals](https://mlsanity.com/paper/2508.05162/) (2025)
- [Beyond Global Alignment: Fine-Grained Motion-Language Retrieval via Pyramidal Shapley-Taylor Learning](https://mlsanity.com/paper/2601.21904/) (2026)
- [SentiAvatar: Towards Expressive and Interactive Digital Humans](https://mlsanity.com/paper/2604.02908/) (2026)
- [MotionHiFlow: Text-to-motion via hierarchical flow matching](https://mlsanity.com/paper/2604.23264/) (2026)
- [ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation](https://mlsanity.com/paper/2605.11704/) (2026)
- [PA-HOI: A Physics-Aware Human and Object Interaction Dataset](https://mlsanity.com/paper/2508.06205/) (2025)
- [Dense Motion Captioning](https://mlsanity.com/paper/2511.05369/) (2025)
- [PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction](https://mlsanity.com/paper/2604.08125/) (2026)
- [Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World](https://mlsanity.com/paper/2511.00041/) (2025)
- [U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation](https://mlsanity.com/paper/2602.23739/) (2026)
- [InterMoE: Individual-Specific 3D Human Interaction Generation via Dynamic Temporal-Selective MoE](https://mlsanity.com/paper/2511.13488/) (2025)
- [OmniMoGen: Unifying Human Motion Generation via Learning from Interleaved Text-Motion Instructions](https://mlsanity.com/paper/2512.19159/) (2025)
- [T2MBench: A Benchmark for Out-of-Distribution Text-to-Motion Generation](https://mlsanity.com/paper/2602.13751/) (2026)
- [ParTY: Part-Guidance for Expressive Text-to-Motion Synthesis](https://mlsanity.com/paper/2603.09611/) (2026)
- [A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting](https://mlsanity.com/paper/2604.13427/) (2026)
- [Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation](https://mlsanity.com/paper/2607.06843/) (2026)
- [One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors](https://mlsanity.com/paper/2510.25241/) (2025)
- [DeMoGen: Towards Decompositional Human Motion Generation with Energy-Based Diffusion Models](https://mlsanity.com/paper/2512.22324/) (2025)
- [Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation](https://mlsanity.com/paper/2601.14788/) (2026)
- [TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generation](https://mlsanity.com/paper/2602.08462/) (2026)
- [InterEdit: Navigating Text-Guided 3D Dyadic Human Motion Editing](https://mlsanity.com/paper/2603.13082/) (2026)
- [Motion-Adapter: A Diffusion Model Adapter for Text-to-Motion Generation of Compound Actions](https://mlsanity.com/paper/2604.16135/) (2026)
- [Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation](https://mlsanity.com/paper/2605.13333/) (2026)
- [Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control](https://mlsanity.com/paper/2605.14935/) (2026)
- [MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation](https://mlsanity.com/paper/2605.18956/) (2026)
- [EMA: Effort Metric Attention for Anatomical Effort-Guided Human Motion Diffusion](https://mlsanity.com/paper/2605.24566/) (2026)

## Abstract (arXiv)

Text-driven motion generation has advanced significantly with the rise of denoising diffusion models. However, previous methods often oversimplify representations for the skeletal joints, temporal frames, and textual words, limiting their ability to fully capture the information within each modality and their interactions. Moreover, when using pre-trained models for downstream tasks, such as editing, they typically require additional efforts, including manual interventions, optimization, or fine-tuning. In this paper, we introduce a skeleton-aware latent diffusion (SALAD), a model that explicitly captures the intricate inter-relationships between joints, frames, and words. Furthermore, by leveraging cross-attention maps produced during the generation process, we enable attention-based zero-shot text-driven motion editing using a pre-trained SALAD model, requiring no additional user input beyond text prompts. Our approach significantly outperforms previous methods in terms of text-motion alignment without compromising generation quality, and demonstrates practical versatility by providing diverse editing capabilities beyond generation. Code is available at project page.