# TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis

arXiv: https://arxiv.org/abs/2307.15042 · HTML: https://mlsanity.com/paper/2307.15042/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 37 of its 60 references that are in the map.
- First posted on arXiv 27 Jul 2023.

## Placed in

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

## Builds on (most cited first, 30 of 37)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [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)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [EDGE: Editable Dance Generation From Music](https://mlsanity.com/paper/2211.10658/) (2022)
- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis](https://mlsanity.com/paper/2212.04495/) (2022)
- [FLAME: Free-form Language-based Motion Synthesis & Editing](https://mlsanity.com/paper/2209.00349/) (2022)
- [DRAW: A Recurrent Neural Network For Image Generation](https://mlsanity.com/paper/1502.04623/) (2015)
- [Character Controllers Using Motion VAEs](https://mlsanity.com/paper/2103.14274/) (2021)
- [Skeleton-Aware Networks for Deep Motion Retargeting](https://mlsanity.com/paper/2005.05732/) (2020)
- [QuaterNet: A Quaternion-based Recurrent Model for Human Motion](https://mlsanity.com/paper/1805.06485/) (2018)
- [Unpaired Motion Style Transfer from Video to Animation](https://mlsanity.com/paper/2005.05751/) (2020)
- [Video (language) modeling: a baseline for generative models of natural videos](https://mlsanity.com/paper/1412.6604/) (2014)

## Built on by (most cited first, 30 of 49)

- [InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion](https://mlsanity.com/paper/2308.16905/) (2023)
- [CG-HOI: Contact-Guided 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2311.16097/) (2023)
- [FIFO-Diffusion: Generating Infinite Videos from Text without Training](https://mlsanity.com/paper/2405.11473/) (2024)
- [State of the Art on Diffusion Models for Visual Computing](https://mlsanity.com/paper/2310.07204/) (2023)
- [Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild](https://mlsanity.com/paper/2406.09905/) (2024)
- [Controllable Human-Object Interaction Synthesis](https://mlsanity.com/paper/2312.03913/) (2023)
- [Rolling Diffusion Models](https://mlsanity.com/paper/2402.09470/) (2024)
- [HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models](https://mlsanity.com/paper/2312.06553/) (2023)
- [Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation](https://mlsanity.com/paper/2401.08559/) (2024)
- [Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression](https://mlsanity.com/paper/2411.16575/) (2024)
- [InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction](https://mlsanity.com/paper/2403.19652/) (2024)
- [Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models](https://mlsanity.com/paper/2406.04806/) (2024)
- [One Diffusion to Generate Them All](https://mlsanity.com/paper/2411.16318/) (2024)
- [Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories](https://mlsanity.com/paper/2505.21851/) (2025)
- [Absolute Coordinates Make Motion Generation Easy](https://mlsanity.com/paper/2505.19377/) (2025)
- [Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control](https://mlsanity.com/paper/2503.11801/) (2025)
- [HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Device](https://mlsanity.com/paper/2409.13426/) (2024)
- [ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation](https://mlsanity.com/paper/2412.18600/) (2024)
- [SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model](https://mlsanity.com/paper/2506.21976/) (2025)
- [SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control](https://mlsanity.com/paper/2412.15664/) (2024)
- [Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control](https://mlsanity.com/paper/2502.12724/) (2025)
- [From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models](https://mlsanity.com/paper/2504.05265/) (2025)
- [FORCE: Physics-aware Human-object Interaction](https://mlsanity.com/paper/2403.11237/) (2024)
- [Zero-Shot Human-Object Interaction Synthesis with Multimodal Priors](https://mlsanity.com/paper/2503.20118/) (2025)
- [ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation](https://mlsanity.com/paper/2607.08741/) (2026)
- [RA-DP: Rapid Adaptive Diffusion Policy for Training-Free High-frequency Robotics Replanning](https://mlsanity.com/paper/2503.04051/) (2025)
- [Compositional Flows for 3D Molecule and Synthesis Pathway Co-design](https://mlsanity.com/paper/2504.08051/) (2025)
- [HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance](https://mlsanity.com/paper/2506.07209/) (2025)
- [Unleashing Guidance Without Classifiers for Human-Object Interaction Animation](https://mlsanity.com/paper/2603.25734/) (2026)
- [TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size](https://mlsanity.com/paper/2603.07988/) (2026)

## Abstract (arXiv)

The gradual nature of a diffusion process that synthesizes samples in small increments constitutes a key ingredient of Denoising Diffusion Probabilistic Models (DDPM), which have presented unprecedented quality in image synthesis and been recently explored in the motion domain. In this work, we propose to adapt the gradual diffusion concept (operating along a diffusion time-axis) into the temporal-axis of the motion sequence. Our key idea is to extend the DDPM framework to support temporally varying denoising, thereby entangling the two axes. Using our special formulation, we iteratively denoise a motion buffer that contains a set of increasingly-noised poses, which auto-regressively produces an arbitrarily long stream of frames. With a stationary diffusion time-axis, in each diffusion step we increment only the temporal-axis of the motion such that the framework produces a new, clean frame which is removed from the beginning of the buffer, followed by a newly drawn noise vector that is appended to it. This new mechanism paves the way towards a new framework for long-term motion synthesis with applications to character animation and other domains.