# ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography

arXiv: https://arxiv.org/abs/2603.22316 · HTML: https://mlsanity.com/paper/2603.22316/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 57 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 30 of 39)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [EDGE: Editable Dance Generation From Music](https://mlsanity.com/paper/2211.10658/) (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)
- [Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory](https://mlsanity.com/paper/2203.13055/) (2022)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [Human Motion Generation: A Survey](https://mlsanity.com/paper/2307.10894/) (2023)
- [FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation](https://mlsanity.com/paper/2212.03741/) (2022)
- [Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning](https://mlsanity.com/paper/2006.06119/) (2020)
- [Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives](https://mlsanity.com/paper/2403.10518/) (2024)
- [AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion](https://mlsanity.com/paper/2503.07418/) (2025)
- [MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space](https://mlsanity.com/paper/2405.16105/) (2024)
- [StreamDiT: Real-Time Streaming Text-to-Video Generation](https://mlsanity.com/paper/2507.03745/) (2025)
- [Motion Anything: Any to Motion Generation](https://mlsanity.com/paper/2503.06955/) (2025)
- [Music-Driven Group Choreography](https://mlsanity.com/paper/2303.12337/) (2023)
- [Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio](https://mlsanity.com/paper/2011.12999/) (2020)
- [A Survey on Human Interaction Motion Generation](https://mlsanity.com/paper/2503.12763/) (2025)
- [DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation](https://mlsanity.com/paper/2308.02915/) (2023)
- [Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation](https://mlsanity.com/paper/1807.01126/) (2018)
- [Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns](https://mlsanity.com/paper/2410.20389/) (2024)
- [Dance Style Transfer with Cross-modal Transformer](https://mlsanity.com/paper/2208.09406/) (2022)
- [Audio Generation with Multiple Conditional Diffusion Model](https://mlsanity.com/paper/2308.11940/) (2023)

## Abstract (arXiv)

Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly relevant to applications such as film production, gaming, and animation. Recent group dance generation models have achieved promising generation quality, but they remain difficult to deploy in interactive scenarios due to bidirectional attention dependencies. As the number of dancers and the sequence length increase, the attention computation required for aligning music conditions with motion sequences grows quadratically, leading to reduced efficiency and increased risk of motion collisions. Effectively modeling dense spatial-temporal interactions is therefore essential, yet existing methods often struggle to capture such complexity, resulting in limited scalability and unstable multi-dancer coordination. To address these challenges, we propose ST-GDance++, a scalable framework that decouples spatial and temporal dependencies to enable efficient and collision-aware group choreography generation. For spatial modeling, we introduce lightweight distance-aware graph convolutions to capture inter-dancer relationships while reducing computational overhead. For temporal modeling, we design a diffusion noise scheduling strategy together with an efficient temporal-aligned attention mask, enabling stream-based generation for long motion sequences and improving scalability in long-duration scenarios. Experiments on the AIOZ-GDance dataset show that ST-GDance++ achieves competitive generation quality with significantly reduced latency compared to existing methods.