# RMD: A Simple Baseline for More General Human Motion Generation via Training-free Retrieval-Augmented Motion Diffuse

arXiv: https://arxiv.org/abs/2412.04343 · HTML: https://mlsanity.com/paper/2412.04343/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2024.

## Built on by (most cited first, 7 of 7)

- [MOSPA: Human Motion Generation Driven by Spatial Audio](https://mlsanity.com/paper/2507.11949/) (2025)
- [ReMoMask: Retrieval-Augmented Masked Motion Generation](https://mlsanity.com/paper/2508.02605/) (2025)
- [Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified Flow](https://mlsanity.com/paper/2509.24099/) (2025)
- [IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation](https://mlsanity.com/paper/2512.10730/) (2025)
- [InterReal: A Unified Physics-Based Imitation Framework for Learning Human-Object Interaction Skills](https://mlsanity.com/paper/2603.07516/) (2026)
- [Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization](https://mlsanity.com/paper/2605.08054/) (2026)
- [ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation](https://mlsanity.com/paper/2609.08365/) (2026)

## Abstract (arXiv)

While motion generation has made substantial progress, its practical application remains constrained by dataset diversity and scale, limiting its ability to handle out-of-distribution scenarios. To address this, we propose a simple and effective baseline, RMD, which enhances the generalization of motion generation through retrieval-augmented techniques. Unlike previous retrieval-based methods, RMD requires no additional training and offers three key advantages: (1) the external retrieval database can be flexibly replaced; (2) body parts from the motion database can be reused, with an LLM facilitating splitting and recombination; and (3) a pre-trained motion diffusion model serves as a prior to improve the quality of motions obtained through retrieval and direct combination. Without any training, RMD achieves state-of-the-art performance, with notable advantages on out-of-distribution data.