# BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation

arXiv: https://arxiv.org/abs/2409.10847 · HTML: https://mlsanity.com/paper/2409.10847/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 35 references that are in the map.
- First posted on arXiv 17 Sep 2024.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [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)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [Efficient Neural Audio Synthesis](https://mlsanity.com/paper/1802.08435/) (2018)
- [Autoregressive Diffusion Models](https://mlsanity.com/paper/2110.02037/) (2021)
- [MMM: Generative Masked Motion Model](https://mlsanity.com/paper/2312.03596/) (2023)
- [AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism](https://mlsanity.com/paper/2309.00796/) (2023)
- [Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation](https://mlsanity.com/paper/2305.09662/) (2023)
- [BAMM: Bidirectional Autoregressive Motion Model](https://mlsanity.com/paper/2403.19435/) (2024)
- [Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model](https://mlsanity.com/paper/2210.12315/) (2022)

## Built on by (most cited first, 13 of 13)

- [Motion Anything: Any to Motion Generation](https://mlsanity.com/paper/2503.06955/) (2025)
- [DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding](https://mlsanity.com/paper/2411.19527/) (2024)
- [Temporal Consistency-Aware Text-to-Motion Generation](https://mlsanity.com/paper/2602.18057/) (2026)
- [ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation](https://mlsanity.com/paper/2605.11704/) (2026)
- [MTVCraft: Tokenizing 4D Motion for Arbitrary Character Animation](https://mlsanity.com/paper/2505.10238/) (2025)
- [MoCLIP: Motion-Aware Fine-Tuning and Distillation of CLIP for Human Motion Generation](https://mlsanity.com/paper/2505.10810/) (2025)
- [Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward](https://mlsanity.com/paper/2506.03191/) (2025)
- [ParTY: Part-Guidance for Expressive Text-to-Motion Synthesis](https://mlsanity.com/paper/2603.09611/) (2026)
- [FlowCoMotion: Text-to-Motion Generation via Token-Latent Flow Modeling](https://mlsanity.com/paper/2604.11083/) (2026)
- [RoleMotion: A Large-Scale Dataset towards Robust Scene-Specific Role-Playing Motion Synthesis with Fine-grained Descriptions](https://mlsanity.com/paper/2512.01582/) (2025)
- [Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation](https://mlsanity.com/paper/2601.14788/) (2026)
- [Multi-Modal Controlled Coherent Motion Generation](https://mlsanity.com/paper/2609.11439/) (2026)
- [UniMo: Unifying Human and Animal Motion Generation](https://mlsanity.com/paper/2609.12342/) (2026)

## Abstract (arXiv)

Autoregressive models excel in modeling sequential dependencies by enforcing causal constraints, yet they struggle to capture complex bidirectional patterns due to their unidirectional nature. In contrast, mask-based models leverage bidirectional context, enabling richer dependency modeling. However, they often assume token independence during prediction, which undermines the modeling of sequential dependencies. Additionally, the corruption of sequences through masking or absorption can introduce unnatural distortions, complicating the learning process. To address these issues, we propose Bidirectional Autoregressive Diffusion (BAD), a novel approach that unifies the strengths of autoregressive and mask-based generative models. BAD utilizes a permutation-based corruption technique that preserves the natural sequence structure while enforcing causal dependencies through randomized ordering, enabling the effective capture of both sequential and bidirectional relationships. Comprehensive experiments show that BAD outperforms autoregressive and mask-based models in text-to-motion generation, suggesting a novel pre-training strategy for sequence modeling. The codebase for BAD is available on https://github.com/RohollahHS/BAD.