# Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment

arXiv: https://arxiv.org/abs/2403.18811 · HTML: https://mlsanity.com/paper/2403.18811/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 62 references that are in the map.
- First posted on arXiv 27 Mar 2024.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [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)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [Embodied Hands: Modeling and Capturing Hands and Bodies Together](https://mlsanity.com/paper/2201.02610/) (2022)
- [TEACH: Temporal Action Composition for 3D Humans](https://mlsanity.com/paper/2209.04066/) (2022)
- [Playing for 3D Human Recovery](https://mlsanity.com/paper/2110.07588/) (2021)
- [AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars](https://mlsanity.com/paper/2205.08535/) (2022)
- [Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations](https://mlsanity.com/paper/2303.13129/) (2023)
- [SoMoFormer: Multi-Person Pose Forecasting with Transformers](https://mlsanity.com/paper/2208.14023/) (2022)

## Built on by (most cited first, 30 of 47)

- [Large Motion Model for Unified Multi-Modal Motion Generation](https://mlsanity.com/paper/2404.01284/) (2024)
- [UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model](https://mlsanity.com/paper/2408.00762/) (2024)
- [Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation](https://mlsanity.com/paper/2502.20370/) (2025)
- [A Survey on Human Interaction Motion Generation](https://mlsanity.com/paper/2503.12763/) (2025)
- [DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling](https://mlsanity.com/paper/2506.18680/) (2025)
- [Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis](https://mlsanity.com/paper/2508.02106/) (2025)
- [SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters](https://mlsanity.com/paper/2412.00174/) (2024)
- [SCENIC: Scene-aware Semantic Navigation with Instruction-guided Control](https://mlsanity.com/paper/2412.15664/) (2024)
- [MOSPA: Human Motion Generation Driven by Spatial Audio](https://mlsanity.com/paper/2507.11949/) (2025)
- [FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation](https://mlsanity.com/paper/2511.21029/) (2025)
- [Synergy and Synchrony in Couple Dances](https://mlsanity.com/paper/2409.04440/) (2024)
- [MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation](https://mlsanity.com/paper/2512.18181/) (2025)
- [3D Human Interaction Generation: A Survey](https://mlsanity.com/paper/2503.13120/) (2025)
- [ARFlow: Human Action-Reaction Flow Matching with Physical Guidance](https://mlsanity.com/paper/2503.16973/) (2025)
- [Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation](https://mlsanity.com/paper/2510.14976/) (2025)
- [DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation](https://mlsanity.com/paper/2602.23165/) (2026)
- [DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions](https://mlsanity.com/paper/2508.17342/) (2025)
- [Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified Flow](https://mlsanity.com/paper/2509.24099/) (2025)
- [MusicInfuser: Making Video Diffusion Listen and Dance](https://mlsanity.com/paper/2503.14505/) (2025)
- [TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size](https://mlsanity.com/paper/2603.07988/) (2026)
- [Half-Physics: Enabling Kinematic 3D Human Model with Physical Interactions](https://mlsanity.com/paper/2507.23778/) (2025)
- [MDD: A Dataset for Text-and-Music Conditioned Duet Dance Generation](https://mlsanity.com/paper/2508.16911/) (2025)
- [Advances in 4D Representation: Geometry, Motion, and Interaction](https://mlsanity.com/paper/2510.19255/) (2025)
- [Diffusion Forcing for Multi-Agent Interaction Sequence Modeling](https://mlsanity.com/paper/2512.17900/) (2025)
- [EverybodyDance: Bipartite Graph-Based Identity Correspondence for Multi-Character Animation](https://mlsanity.com/paper/2512.16360/) (2025)
- [PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction](https://mlsanity.com/paper/2604.08125/) (2026)
- [CoMPAS3D: A Dataset and Benchmark for Interactive Motion](https://mlsanity.com/paper/2507.19684/) (2025)
- [Learning to Generate Human-Human-Object Interactions from Textual Descriptions](https://mlsanity.com/paper/2511.20446/) (2025)
- [UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Framework](https://mlsanity.com/paper/2512.03918/) (2025)
- [U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation](https://mlsanity.com/paper/2602.23739/) (2026)

## Abstract (arXiv)

We introduce a novel task within the field of 3D dance generation, termed dance accompaniment, which necessitates the generation of responsive movements from a dance partner, the "follower", synchronized with the lead dancer's movements and the underlying musical rhythm. Unlike existing solo or group dance generation tasks, a duet dance scenario entails a heightened degree of interaction between the two participants, requiring delicate coordination in both pose and position. To support this task, we first build a large-scale and diverse duet interactive dance dataset, DD100, by recording about 117 minutes of professional dancers' performances. To address the challenges inherent in this task, we propose a GPT-based model, Duolando, which autoregressively predicts the subsequent tokenized motion conditioned on the coordinated information of the music, the leader's and the follower's movements. To further enhance the GPT's capabilities of generating stable results on unseen conditions (music and leader motions), we devise an off-policy reinforcement learning strategy that allows the model to explore viable trajectories from out-of-distribution samplings, guided by human-defined rewards. Based on the collected dataset and proposed method, we establish a benchmark with several carefully designed metrics.