# UniMo: Unifying Human and Animal Motion Generation

arXiv: https://arxiv.org/abs/2609.12342 · HTML: https://mlsanity.com/paper/2609.12342/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [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)
- [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)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose](https://mlsanity.com/paper/2108.10842/) (2021)
- [Motion Anything: Any to Motion Generation](https://mlsanity.com/paper/2503.06955/) (2025)
- [MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling](https://mlsanity.com/paper/2409.17686/) (2024)
- [AnyTop: Character Animation Diffusion with Any Topology](https://mlsanity.com/paper/2502.17327/) (2025)
- [DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion](https://mlsanity.com/paper/2309.01372/) (2023)
- [Neural3Points: Learning to Generate Physically Realistic Full-body Motion for Virtual Reality Users](https://mlsanity.com/paper/2209.05753/) (2022)
- [OmniMotionGPT: Animal Motion Generation with Limited Data](https://mlsanity.com/paper/2311.18303/) (2023)
- [Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion](https://mlsanity.com/paper/2405.11286/) (2024)
- [Example-based Motion Synthesis via Generative Motion Matching](https://mlsanity.com/paper/2306.00378/) (2023)
- [KMM: Key Frame Mask Mamba for Extended Motion Generation](https://mlsanity.com/paper/2411.06481/) (2024)
- [BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation](https://mlsanity.com/paper/2409.10847/) (2024)
- [DreamCinema: Cinematic Transfer with Free Camera and 3D Character](https://mlsanity.com/paper/2408.12601/) (2024)
- [MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer](https://mlsanity.com/paper/2504.08959/) (2025)
- [Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models](https://mlsanity.com/paper/1910.06699/) (2019)
- [BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis](https://mlsanity.com/paper/2412.00112/) (2024)

## Abstract (arXiv)

The conditional generation of 3D motion has emerged as a key research topic due to its wide applicability across robotics, AR/VR, gaming, and content creation. However, extending recent advances in text-driven human motion generation to the animal domain remains challenging due to two core limitations. First, animals exhibit highly diverse skeletal topologies, unlike the standard human structure, making unified modeling across species difficult and leading to inefficient per-species models. Second, existing animal motion datasets suffer from limited scale and annotation quality, constraining model performance. To address these challenges, we propose UniMo, a unified point cloud-based motion generation framework that bypasses topological discrepancies by converting parametric skeletons into unparametric representations, further enhanced by dynamic sampling that allocates more points to active joints. Additionally, we present UniML3D, a large-scale motion-language dataset spanning both human and animal categories, containing 145,907 motion sequences and 433,388 captions-over 102x larger than existing animal datasets. Our method achieves state-of-the-art results on UniML3D and three public benchmarks including HumanML3D, KIT-ML, and AnimalML3D, demonstrating the feasibility and effectiveness of unified human-animal motion generation. Website: https://steve-zeyu-zhang.github.io/UniMo.