# FloodDiffusion: Tailored Diffusion Forcing for Streaming Motion Generation

arXiv: https://arxiv.org/abs/2512.03520 · HTML: https://mlsanity.com/paper/2512.03520/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 43 references that are in the map.
- First posted on arXiv 3 Dec 2025.

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

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [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)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [BABEL: Bodies, Action and Behavior with English Labels](https://mlsanity.com/paper/2106.09696/) (2021)
- [Diffusion Probabilistic Modeling for Video Generation](https://mlsanity.com/paper/2203.09481/) (2022)
- [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025)
- [SkyReels-V2: Infinite-length Film Generative Model](https://mlsanity.com/paper/2504.13074/) (2025)
- [MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space](https://mlsanity.com/paper/2503.15451/) (2025)
- [Seamless Human Motion Composition with Blended Positional Encodings](https://mlsanity.com/paper/2402.15509/) (2024)
- [Progressive Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2410.08151/) (2024)
- [StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation](https://mlsanity.com/paper/2312.12491/) (2023)
- [AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion](https://mlsanity.com/paper/2503.07418/) (2025)

## Built on by (most cited first, 16 of 16)

- [TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control](https://mlsanity.com/paper/2602.07439/) (2026)
- [PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakers](https://mlsanity.com/paper/2605.06064/) (2026)
- [ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning](https://mlsanity.com/paper/2603.13500/) (2026)
- [ProAct: Harnessing Streaming Motion Generation and Agentic Reasoning for Real-Time Embodied Social Interaction](https://mlsanity.com/paper/2602.14048/) (2026)
- [Refining Compositional Diffusion for Reliable Long-Horizon Planning](https://mlsanity.com/paper/2605.03075/) (2026)
- [DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing](https://mlsanity.com/paper/2605.28491/) (2026)
- [InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation](https://mlsanity.com/paper/2607.10287/) (2026)
- [ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography](https://mlsanity.com/paper/2603.22316/) (2026)
- [InterSing: Explicit Interaction Dynamics for 3D Duet Singing Animation and Beyond](https://mlsanity.com/paper/2609.04903/) (2026)
- [Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion](https://mlsanity.com/paper/2609.30795/) (2026)
- [FloodDiffusion 2: Efficient and Path Controllable Streaming Motion Generation](https://mlsanity.com/paper/2609.33167/) (2026)
- [MotionSpaceFlow: Representation-Aware Flow Matching in Direct Motion Space](https://mlsanity.com/paper/2609.34190/) (2026)
- [Triangular Resampling for Long-Horizon Motion Generation](https://mlsanity.com/paper/2609.34697/) (2026)
- [World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories](https://mlsanity.com/paper/2610.01742/) (2026)
- [Streaming Multi-Track Timeline Control for 3D Human Motion Generation](https://mlsanity.com/paper/2610.03873/) (2026)
- [Sonic-AMG: Streaming Human Motion Generation from Spatial Audio](https://mlsanity.com/paper/2610.13300/) (2026)

## Abstract (arXiv)

We present FloodDiffusion, a new framework for text-driven, streaming human motion generation. Given time-varying text prompts, FloodDiffusion generates text-aligned, seamless motion sequences with real-time latency. Unlike existing methods that rely on chunk-by-chunk or auto-regressive model with diffusion head, we adopt a diffusion forcing framework to model this time-series generation task under time-varying control events. We find that a straightforward implementation of vanilla diffusion forcing (as proposed for video models) fails to model real motion distributions. We demonstrate that to guarantee modeling the output distribution, the vanilla diffusion forcing must be tailored to: (i) train with a bi-directional attention instead of casual attention; (ii) implement a lower triangular time scheduler instead of a random one; (iii) utilize a continues time-varying way to introduce text conditioning. With these improvements, we demonstrate in the first time that the diffusion forcing-based framework achieves state-of-the-art performance on the streaming motion generation task, reaching an FID of 0.057 on the HumanML3D benchmark. Models, code, and weights are available. https://shandaai.github.io/FloodDiffusion/