mlsanityData to 14 Oct 2026

HuTuMotion: Human-Tuned Navigation of Latent Motion Diffusion Models with Minimal Feedback

arXiv 2312.12227 ↗First posted 19 Dec 2023cs.CV cs.AIcited by 6

On the map: Diffusion models → Video generation

also in 1 more
Abstract (arXiv)

We introduce HuTuMotion, an innovative approach for generating natural human motions that navigates latent motion diffusion models by leveraging few-shot human feedback. Unlike existing approaches that sample latent variables from a standard normal prior distribution, our method adapts the prior distribution to better suit the characteristics of the data, as indicated by human feedback, thus enhancing the quality of motion generation. Furthermore, our findings reveal that utilizing few-shot feedback can yield performance levels on par with those attained through extensive human feedback. This discovery emphasizes the potential and efficiency of incorporating few-shot human-guided optimization within latent diffusion models for personalized and style-aware human motion generation applications. The experimental results show the significantly superior performance of our method over existing state-of-the-art approaches.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 33 of its 46 references that are in the map. First posted on arXiv 19 Dec 2023.

Builds on

33 of 46 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Executing your Commands via Motion Diffusion in Latent Space8 Dec
  2. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model31 Aug

Other references · 31

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2022Classifier-Free Diffusion Guidancecited by 5,847
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  8. 2020Learning to summarize from human feedbackcited by 2,588
  9. 2016Matching Networks for One Shot Learningcited by 2,255
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  11. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  12. 2017End-to-end Recovery of Human Shape and Posecited by 885
19 more
  1. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 501
  2. 2023Aligning Text-to-Image Models using Human Feedbackcited by 422
  3. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  4. 2022TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Textscited by 359
  5. 2016The KIT Motion-Language Datasetcited by 338
  6. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  7. 2021Character Controllers Using Motion VAEscited by 184
  8. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 178
  9. 2023HIVE: Harnessing Human Feedback for Instructional Visual Editingcited by 173
  10. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  11. 2021DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformercited by 111
  12. 2021Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agentscited by 106
  13. 2018Multi-level Semantic Feature Augmentation for One-shot Learningcited by 62
  14. 2017Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networkscited by 61
  15. 2022MoDi: Unconditional Motion Synthesis from Diverse Datacited by 59
  16. 2023ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstructioncited by 37
  17. 2023Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oraclescited by 35
  18. 2022Few-Shot Classification with Contrastive Learningcited by 31
  19. 2023TapMo: Shape-aware Motion Generation of Skeleton-free Characterscited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 2.

6 papers.

  1. 2024ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Modelcited by 26
  2. 2024Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motioncited by 16
  3. 2024ExpGest: Expressive Speaker Generation Using Diffusion Model and Hybrid Audio-Text Guidancecited by 2
  4. 2025From 2D Alignment to 3D Plausibility: Unifying Heterogeneous 2D Priors and Penetration-Free Diffusion for Occlusion-Robust Two-Hand Reconstructioncited by 0
  5. 2026MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanationcited by 0
  6. 2026Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GANcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models
  2. 2026Diffusion Path Alignment for Long-Range Motion Generation and Domain Transitions
  3. 2024Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression
  4. 2025Unconditional Human Motion and Shape Generation via Balanced Score-Based Diffusion
  5. 2022Human Motion Diffusion Model
  6. 2023Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models
  7. 2022Pretrained Diffusion Models for Unified Human Motion Synthesis
  8. 2025Back to Basics: Motion Representation Matters for Human Motion Generation Using Diffusion Model