mlsanityData to 14 Oct 2026

Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations

arXiv 2312.11442 ↗First posted 18 Dec 2023cs.HC cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

This paper presents an Exploratory 3D Dance generation framework, E3D2, designed to address the exploration capability deficiency in existing music-conditioned 3D dance generation models. Current models often generate monotonous and simplistic dance sequences that misalign with human preferences because they lack exploration capabilities. The E3D2 framework involves a reward model trained from automatically-ranked dance demonstrations, which then guides the reinforcement learning process. This approach encourages the agent to explore and generate high quality and diverse dance movement sequences. The soundness of the reward model is both theoretically and experimentally validated. Empirical experiments demonstrate the effectiveness of E3D2 on the AIST++ dataset. Project Page: https://sites.google.com/view/e3d2.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 33 of its 66 references that are in the map. First posted on arXiv 18 Dec 2023.

Builds on

33 of 66 references.

References · 33

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2017Deep reinforcement learning from human preferencescited by 3,912
  4. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  5. 2020Learning to summarize from human feedbackcited by 2,588
  6. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  7. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  8. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  9. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 644
  10. 2022Improving alignment of dialogue agents via targeted human judgementscited by 531
  11. 2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 485
  12. 2018Reward learning from human preferences and demonstrations in Ataricited by 316
21 more
  1. 2022Teaching language models to support answers with verified quotescited by 292
  2. 2021Recursively Summarizing Books with Human Feedbackcited by 290
  3. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 260
  4. 2022Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memorycited by 212
  5. 2017Interactive Learning from Policy-Dependent Human Feedbackcited by 158
  6. 2022Prompting Decision Transformer for Few-Shot Policy Generalizationcited by 146
  7. 2017Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spacescited by 123
  8. 2021DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformercited by 111
  9. 2022Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generationcited by 107
  10. 2017Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Rewardcited by 105
  11. 2022Few-Shot Preference Learning for Human-in-the-Loop RLcited by 87
  12. 2020Learning to Generate Diverse Dance Motions with Transformercited by 85
  13. 2020Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learningcited by 81
  14. 2023Preference Transformer: Modeling Human Preferences using Transformers for RLcited by 79
  15. 2019Learning to Paint With Model-based Deep Reinforcement Learningcited by 71
  16. 2019Combating the Compounding-Error Problem with a Multi-step Modelcited by 54
  17. 2020ChoreoNet: Towards Music to Dance Synthesis with Choreographic Action Unitcited by 31
  18. 2018Inverse reinforcement learning for video gamescited by 26
  19. 2021Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminabilitycited by 19
  20. 2022ChoreoGraph: Music-conditioned Automatic Dance Choreography over a Style and Tempo Consistent Dynamic Graphcited by 17
  21. 2019Generative Autoregressive Networks for 3D Dancing Move Synthesis from Musiccited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 3.

8 papers.

  1. 2024Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Modelcited by 35
  2. 2024Exploring Text-to-Motion Generation with Human Preferencecited by 8
  3. 2025Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representationcited by 8
  4. 2025Tempo as the Stable Cue: Hierarchical Mixture of Tempo and Beat Experts for Music to 3D Dance Generationcited by 3
  5. 2026EchoAvatar: Real-time Generative Avatar Animation from Audio Streamscited by 2
  6. 2025Continuous Vision-Language-Action Co-Learning with Semantic-Physical Alignment for Behavioral Cloningcited by 1
  7. 2026FlowDance: Music-Driven Dance Video Generation with Parallel Pose and RGB Streamscited by 0
  8. 2026BeatDance: Generating Beat-Consistent 3D Dance with Hierarchical Spatial-Temporal Modelingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Skeleton2Stage: Reward-Guided Fine-Tuning for Physically Plausible Dance Generation
  2. 2024Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment
  3. 2024May the Dance be with You: Dance Generation Framework for Non-Humanoids
  4. 2026CustomDance: Customized 3D Dance Generation with Coarse-to-Fine Human-Centered Interactive Control ↗
  5. 2023EnchantDance: Unveiling the Potential of Music-Driven Dance Movement
  6. 2025MATHDance: Mamba-Transformer Architecture with Uniform Tokenization for High-Quality 3D Dance Generation
  7. 2025MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation
  8. 2023LongDanceDiff: Long-term Dance Generation with Conditional Diffusion Model