# Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression

arXiv: https://arxiv.org/abs/2411.16575 · HTML: https://mlsanity.com/paper/2411.16575/

## Key facts

- Cited by 85 papers in the map (data through 14 Oct 2026).
- Builds on 96 of its 120 references that are in the map.
- First posted on arXiv 25 Nov 2024.

## Builds on (most cited first, 30 of 96)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [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)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)

## Built on by (most cited first, 30 of 85)

- [SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control](https://mlsanity.com/paper/2511.07820/) (2025)
- [MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space](https://mlsanity.com/paper/2503.15451/) (2025)
- [Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data](https://mlsanity.com/paper/2507.07095/) (2025)
- [SnapMoGen: Human Motion Generation from Expressive Texts](https://mlsanity.com/paper/2507.09122/) (2025)
- [Absolute Coordinates Make Motion Generation Easy](https://mlsanity.com/paper/2505.19377/) (2025)
- [From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance](https://mlsanity.com/paper/2510.14952/) (2025)
- [EgoTwin: Dreaming Body and View in First Person](https://mlsanity.com/paper/2508.13013/) (2025)
- [LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens](https://mlsanity.com/paper/2602.12370/) (2026)
- [FrankenMotion: Part-level Human Motion Generation and Composition](https://mlsanity.com/paper/2601.10909/) (2026)
- [Causal Motion Diffusion Models for Autoregressive Motion Generation](https://mlsanity.com/paper/2602.22594/) (2026)
- [ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model](https://mlsanity.com/paper/2506.02452/) (2025)
- [Motion Generation: A Survey of Generative Approaches and Benchmarks](https://mlsanity.com/paper/2507.05419/) (2025)
- [Pulp Motion: Framing-aware multimodal camera and human motion generation](https://mlsanity.com/paper/2510.05097/) (2025)
- [ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation](https://mlsanity.com/paper/2607.08741/) (2026)
- [BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis](https://mlsanity.com/paper/2412.00112/) (2024)
- [IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation](https://mlsanity.com/paper/2512.10730/) (2025)
- [Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models](https://mlsanity.com/paper/2512.19692/) (2025)
- [CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos](https://mlsanity.com/paper/2601.10632/) (2026)
- [MoSa: Motion Generation with Scalable Autoregressive Modeling](https://mlsanity.com/paper/2511.01200/) (2025)
- [ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control](https://mlsanity.com/paper/2602.22742/) (2026)
- [ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning](https://mlsanity.com/paper/2603.13500/) (2026)
- [PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation](https://mlsanity.com/paper/2506.07456/) (2025)
- [X-MoGen: Unified Motion Generation across Humans and Animals](https://mlsanity.com/paper/2508.05162/) (2025)
- [MDD: A Dataset for Text-and-Music Conditioned Duet Dance Generation](https://mlsanity.com/paper/2508.16911/) (2025)
- [MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling](https://mlsanity.com/paper/2508.17404/) (2025)
- [SMooGPT: Stylized Motion Generation using Large Language Models](https://mlsanity.com/paper/2509.04058/) (2025)
- [MaDiS: Taming Masked Diffusion Language Models for Sign Language Generation](https://mlsanity.com/paper/2601.19577/) (2026)
- [EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation](https://mlsanity.com/paper/2602.07967/) (2026)
- [Next-Scale Autoregressive Models for Text-to-Motion Generation](https://mlsanity.com/paper/2604.03799/) (2026)
- [MotionHiFlow: Text-to-motion via hierarchical flow matching](https://mlsanity.com/paper/2604.23264/) (2026)

## Abstract (arXiv)

Since 2023, Vector Quantization (VQ)-based discrete generation methods have rapidly dominated human motion generation, primarily surpassing diffusion-based continuous generation methods in standard performance metrics. However, VQ-based methods have inherent limitations. Representing continuous motion data as limited discrete tokens leads to inevitable information loss, reduces the diversity of generated motions, and restricts their ability to function effectively as motion priors or generation guidance. In contrast, the continuous space generation nature of diffusion-based methods makes them well-suited to address these limitations and with even potential for model scalability. In this work, we systematically investigate why current VQ-based methods perform well and explore the limitations of existing diffusion-based methods from the perspective of motion data representation and distribution. Drawing on these insights, we preserve the inherent strengths of a diffusion-based human motion generation model and gradually optimize it with inspiration from VQ-based approaches. Our approach introduces a human motion diffusion model enabled to perform masked autoregression, optimized with a reformed data representation and distribution. Additionally, we propose a more robust evaluation method to assess different approaches. Extensive experiments on various datasets demonstrate our method outperforms previous methods and achieves state-of-the-art performances.