# Parasitic Co-Denoising: Unlocking 3D Human Motion Generation in a Frozen Video Diffusion Model

arXiv: https://arxiv.org/abs/2610.03047 · HTML: https://mlsanity.com/paper/2610.03047/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 28 of its 39 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (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)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [OmniControl: Control Any Joint at Any Time for Human Motion Generation](https://mlsanity.com/paper/2310.08580/) (2023)
- [MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model](https://mlsanity.com/paper/2404.19759/) (2024)
- [Denoising Diffusion Autoencoders are Unified Self-supervised Learners](https://mlsanity.com/paper/2303.09769/) (2023)
- [HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation](https://mlsanity.com/paper/2512.23464/) (2025)
- [MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities](https://mlsanity.com/paper/2504.02478/) (2025)
- [A Survey on Deep Learning for Skeleton-Based Human Animation](https://mlsanity.com/paper/2110.06901/) (2021)
- [MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls](https://mlsanity.com/paper/2407.21136/) (2024)
- [Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation](https://mlsanity.com/paper/2412.11193/) (2024)
- [The Quest for Generalizable Motion Generation: Data, Model, and Evaluation](https://mlsanity.com/paper/2510.26794/) (2025)
- [DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding](https://mlsanity.com/paper/2411.19527/) (2024)
- [ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment](https://mlsanity.com/paper/2511.19217/) (2025)
- [EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer](https://mlsanity.com/paper/2512.18814/) (2025)
- [Causal Motion Diffusion Models for Autoregressive Motion Generation](https://mlsanity.com/paper/2602.22594/) (2026)
- [GenM3: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation](https://mlsanity.com/paper/2503.14919/) (2025)
- [MotionVLA: Vision-Language-Action Model for Humanoid Motion](https://mlsanity.com/paper/2606.15142/) (2026)

## Abstract (arXiv)

Despite never being supervised on explicit 3D motion, large-scale text-to-video diffusion models synthesize realistic human motion in their generated videos. We ask whether this implicit knowledge can be turned into explicit 3D motion generation, without training a separate motion model. Probing a frozen Wan2.1 reveals that a recoverable motion signal is present in its intermediate states across the entire denoising schedule, not confined to the clean output. Motivated by this, we introduce parasitic co-denoising, a paradigm in which motion is decoded from the host model along its denoising schedule rather than produced by an independent generator. We instantiate it as the Parasitic Motion Decoder (PMD), an efficient flow-matching decoder that shares the host's noise schedule and reads its intermediate features through a σ-adaptive multi-layer fusion, leaving the host unmodified. Drawing its coverage from the host rather than from motion data, PMD leads dedicated motion generators on text-motion alignment at a small fraction of their trainable parameters, while producing paired video and motion in a single pass that motion-only baselines cannot match.