# MixerMDM: Learnable Composition of Human Motion Diffusion Models

arXiv: https://arxiv.org/abs/2504.01019 · HTML: https://mlsanity.com/paper/2504.01019/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 58 of its 69 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Placed in

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

## Builds on (most cited first, 30 of 58)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (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)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [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)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (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)
- [Language2Pose: Natural Language Grounded Pose Forecasting](https://mlsanity.com/paper/1907.01108/) (2019)
- [FLAME: Free-form Language-based Motion Synthesis & Editing](https://mlsanity.com/paper/2209.00349/) (2022)

## Built on by (most cited first, 13 of 13)

- [Absolute Coordinates Make Motion Generation Easy](https://mlsanity.com/paper/2505.19377/) (2025)
- [FrankenMotion: Part-level Human Motion Generation and Composition](https://mlsanity.com/paper/2601.10909/) (2026)
- [Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models](https://mlsanity.com/paper/2512.19692/) (2025)
- [Topology-Agnostic Animal Motion Generation from Text Prompt](https://mlsanity.com/paper/2512.10352/) (2025)
- [U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation](https://mlsanity.com/paper/2602.23739/) (2026)
- [Not All Frames Are Equal: Complexity-Aware Masked Motion Generation via Motion Spectral Descriptors](https://mlsanity.com/paper/2603.29655/) (2026)
- [Envisioning the Future, One Step at a Time](https://mlsanity.com/paper/2604.09527/) (2026)
- [Dex2HOI: Dexterous Bimanual Two-Object Interaction Generation](https://mlsanity.com/paper/2605.30444/) (2026)
- [Social Structure Matters in 3D Human-Human Interaction Generation](https://mlsanity.com/paper/2606.24255/) (2026)
- [Unified Number-Free Text-to-Motion Generation Via Flow Matching](https://mlsanity.com/paper/2603.27040/) (2026)
- [PoseShield: Neural Collision Fields for Human Self-Collision Resolution](https://mlsanity.com/paper/2606.29686/) (2026)
- [ARMS: Anchor-Relational Motion Streaming for Seamless Solo-Social Motion Transitions](https://mlsanity.com/paper/2607.05733/) (2026)
- [BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion](https://mlsanity.com/paper/2609.35407/) (2026)

## Abstract (arXiv)

Generating human motion guided by conditions such as textual descriptions is challenging due to the need for datasets with pairs of high-quality motion and their corresponding conditions. The difficulty increases when aiming for finer control in the generation. To that end, prior works have proposed to combine several motion diffusion models pre-trained on datasets with different types of conditions, thus allowing control with multiple conditions. However, the proposed merging strategies overlook that the optimal way to combine the generation processes might depend on the particularities of each pre-trained generative model and also the specific textual descriptions. In this context, we introduce MixerMDM, the first learnable model composition technique for combining pre-trained text-conditioned human motion diffusion models. Unlike previous approaches, MixerMDM provides a dynamic mixing strategy that is trained in an adversarial fashion to learn to combine the denoising process of each model depending on the set of conditions driving the generation. By using MixerMDM to combine single- and multi-person motion diffusion models, we achieve fine-grained control on the dynamics of every person individually, and also on the overall interaction. Furthermore, we propose a new evaluation technique that, for the first time in this task, measures the interaction and individual quality by computing the alignment between the mixed generated motions and their conditions as well as the capabilities of MixerMDM to adapt the mixing throughout the denoising process depending on the motions to mix.