# EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion

arXiv: https://arxiv.org/abs/2607.10984 · HTML: https://mlsanity.com/paper/2607.10984/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 20 of its 142 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Placed in

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

## Builds on (most cited first, 20 of 20)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Project Aria: A New Tool for Egocentric Multi-Modal AI Research](https://mlsanity.com/paper/2308.13561/) (2023)
- [QuaterNet: A Quaternion-based Recurrent Model for Human Motion](https://mlsanity.com/paper/1805.06485/) (2018)
- [On the Benefits of Invariance in Neural Networks](https://mlsanity.com/paper/2005.00178/) (2020)
- [Learning Character-Agnostic Motion for Motion Retargeting in 2D](https://mlsanity.com/paper/1905.01680/) (2019)
- [Learning with 3D rotations, a hitchhiker's guide to SO(3)](https://mlsanity.com/paper/2404.11735/) (2024)
- [DISCO: accurate Discrete Scale Convolutions](https://mlsanity.com/paper/2106.02733/) (2021)
- [The general theory of permutation equivarant neural networks and higher order graph variational encoders](https://mlsanity.com/paper/2004.03990/) (2020)
- [HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAE](https://mlsanity.com/paper/2204.01565/) (2022)
- [Equivariant Diffusion for Crystal Structure Prediction](https://mlsanity.com/paper/2512.07289/) (2025)
- [Scale-Equivariant Deep Learning for 3D Data](https://mlsanity.com/paper/2304.05864/) (2023)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [HMPO: Human Motion Prediction in Occluded Environments for Safe Motion Planning](https://mlsanity.com/paper/2006.00424/) (2020)
- [HuMoT: Human Motion Representation using Topology-Agnostic Transformers for Character Animation Retargeting](https://mlsanity.com/paper/2305.18897/) (2023)
- [Multi-Embodiment Robotic Retargeting via Guided Diffusion Model](https://mlsanity.com/paper/2505.20857/) (2025)
- [MoReFlow: Motion Retargeting Learning through Unsupervised Flow Matching](https://mlsanity.com/paper/2509.25600/) (2025)
- [StrengthSense: A Dataset of IMU Signals Capturing Everyday Strength-Demanding Activities](https://mlsanity.com/paper/2511.02027/) (2025)

## Built on by (most cited first, 1 of 1)

- [Skeletons in Flow: Graph Structured Flow Matching for Human Motion Prediction](https://mlsanity.com/paper/2609.32231/) (2026)

## Abstract (arXiv)

Existing Stochastic 3D Human Motion Prediction models are fundamentally constrained by hard-coding the skeleton kinematics, severely limiting generalization, preventing cross-dataset training, and requiring complex data retargeting. We introduce EquiFusion, the first kinematics-agnostic model to solve this bottleneck, implementing a latent diffusion model with a permutation equivariant architecture. EquiFusion treats the kinematics' connectivity as an explicit input parameter, ensuring its internal computations are inherently agnostic to joint ordering and graph structure. This novel design enables truly cross-dataset generalization to unseen kinematics and unlocks novel zero-shot directions, such as motion prediction from partial or occluded observations and targeted limb generation. EquiFusion achieves state-of-the-art results on major benchmarks, being up to 75% more compact than previous kinematics-specific methods, while achieving faster training and inference. EquiFusion thus establishes a new, flexible standard for robust human motion prediction. Model and training code are available at https://ceveloper.github.io/publications/equifusion/.