# Breaking the Group Size Barrier: Parameter-Efficient Group Dance Generation with Chain-of-Dancers

arXiv: https://arxiv.org/abs/2610.11237 · HTML: https://mlsanity.com/paper/2610.11237/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 44 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 2 of 2)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [DanceChat: Large Language Model-Guided Music-to-Dance Generation](https://mlsanity.com/paper/2506.10574/) (2025)

## Abstract (arXiv)

Group dance generation aims to synthesize coordinated multi-dancer choreography from music, with broad applications in animation and interactive content creation. This task requires modeling dense inter-person dependencies to ensure spatial coordination, while naturally preserving individual dancer identities. Existing approaches model all dancers jointly with end-to-end transformers, which tie the architecture to a fixed group size and entangle per-dancer identities across frames. We propose ChainDance, a scalable framework that reformulates group dance generation as a Chain-of-Dancers: a sequential decomposition over per-dancer conditional distributions, allowing a single model to scale across variable group sizes without retraining and naturally preserving per-dancer identity. Built on a frozen single-dancer diffusion backbone, ChainDance introduces two lightweight modules: a Role-Aware Text Encoder (RATE) for per-dancer semantic conditioning, and a Group-Aware Motion Encoder (GAME) that aggregates previously generated dancers via a distance-weighted graph convolutional network, and incorporates a training-free noise optimization procedure at inference time to enforce global spatial coherence. Experiments on AIOZ-GDance demonstrate that ChainDance achieves state-of-the-art motion quality and group coordination while structurally preserving per-dancer identity, with 3-4× fewer parameters and requiring 3-6× less training time compared to prior approaches.