# M3GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation

arXiv: https://arxiv.org/abs/2405.16273 · HTML: https://mlsanity.com/paper/2405.16273/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 63 references that are in the map.
- First posted on arXiv 25 May 2024.

## Builds on (most cited first, 30 of 50)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [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)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [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)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [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)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [EDGE: Editable Dance Generation From Music](https://mlsanity.com/paper/2211.10658/) (2022)
- [Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset](https://mlsanity.com/paper/2307.00818/) (2023)
- [AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling](https://mlsanity.com/paper/2402.12226/) (2024)
- [Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory](https://mlsanity.com/paper/2203.13055/) (2022)
- [Self-Correction for Human Parsing](https://mlsanity.com/paper/1910.09777/) (2019)
- [MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model](https://mlsanity.com/paper/2404.19759/) (2024)
- [A Unified Sequence Interface for Vision Tasks](https://mlsanity.com/paper/2206.07669/) (2022)
- [MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators](https://mlsanity.com/paper/2306.10900/) (2023)
- [We are More than Our Joints: Predicting how 3D Bodies Move](https://mlsanity.com/paper/2012.00619/) (2020)
- [Deep representation learning for human motion prediction and classification](https://mlsanity.com/paper/1702.07486/) (2017)

## Built on by (most cited first, 30 of 38)

- [MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding](https://mlsanity.com/paper/2410.21747/) (2024)
- [GENMO: A GENeralist Model for Human MOtion](https://mlsanity.com/paper/2505.01425/) (2025)
- [MotionGPT3: Human Motion as a Second Modality](https://mlsanity.com/paper/2506.24086/) (2025)
- [MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm](https://mlsanity.com/paper/2502.02358/) (2025)
- [MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities](https://mlsanity.com/paper/2504.02478/) (2025)
- [From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities](https://mlsanity.com/paper/2412.11694/) (2024)
- [UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing](https://mlsanity.com/paper/2411.16781/) (2024)
- [SocialGen: Modeling Multi-Human Social Interaction with Language Models](https://mlsanity.com/paper/2503.22906/) (2025)
- [Human-Centric Foundation Models: Perception, Generation and Agentic Modeling](https://mlsanity.com/paper/2502.08556/) (2025)
- [Motion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models](https://mlsanity.com/paper/2507.20220/) (2025)
- [Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model](https://mlsanity.com/paper/2508.07863/) (2025)
- [Motion Generation: A Survey of Generative Approaches and Benchmarks](https://mlsanity.com/paper/2507.05419/) (2025)
- [ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data](https://mlsanity.com/paper/2603.09170/) (2026)
- [HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding](https://mlsanity.com/paper/2503.12955/) (2025)
- [DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions](https://mlsanity.com/paper/2508.17342/) (2025)
- [IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation](https://mlsanity.com/paper/2512.10730/) (2025)
- [A Unified Framework for Motion Reasoning and Generation in Human Interaction](https://mlsanity.com/paper/2410.05628/) (2024)
- [MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing](https://mlsanity.com/paper/2509.23635/) (2025)
- [UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots](https://mlsanity.com/paper/2512.24321/) (2025)
- [UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors](https://mlsanity.com/paper/2603.15975/) (2026)
- [OmniMotion-X: Versatile Multimodal Whole-Body Motion Generation](https://mlsanity.com/paper/2510.19789/) (2025)
- [HMVLM: Human Motion-Vision-Lanuage Model via MoE LoRA](https://mlsanity.com/paper/2511.01463/) (2025)
- [CoordSpeaker: Exploiting Gesture Captioning for Coordinated Caption-Empowered Co-Speech Gesture Generation](https://mlsanity.com/paper/2511.22863/) (2025)
- [OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression](https://mlsanity.com/paper/2510.14954/) (2025)
- [PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction](https://mlsanity.com/paper/2604.08125/) (2026)
- [UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Framework](https://mlsanity.com/paper/2512.03918/) (2025)
- [Grounding Intelligence in Movement](https://mlsanity.com/paper/2507.02771/) (2025)
- [Prime and Reach: Synthesising Body Motion for Gaze-Primed Object Reach](https://mlsanity.com/paper/2512.16456/) (2025)
- [InfiniteDance: Scalable 3D Dance Generation Towards in-the-wild Generalization](https://mlsanity.com/paper/2603.13375/) (2026)
- [BiomechGPT: Extending Motion-Language Models to Clinical Motion Understanding](https://mlsanity.com/paper/2505.18465/) (2025)

## Abstract (arXiv)

This paper presents M3GPT, an advanced Multimodal, Multitask framework for Motion comprehension and generation. M3GPT operates on three fundamental principles. The first focuses on creating a unified representation space for various motion-relevant modalities. We employ discrete vector quantization for multimodal conditional signals, such as text, music and motion/dance, enabling seamless integration into a large language model (LLM) with a single vocabulary. The second involves modeling motion generation directly in the raw motion space. This strategy circumvents the information loss associated with a discrete tokenizer, resulting in more detailed and comprehensive motion generation. Third, M3GPT learns to model the connections and synergies among various motion-relevant tasks. Text, the most familiar and well-understood modality for LLMs, is utilized as a bridge to establish connections between different motion tasks, facilitating mutual reinforcement. To our knowledge, M3GPT is the first model capable of comprehending and generating motions based on multiple signals. Extensive experiments highlight M3GPT's superior performance across various motion-relevant tasks and its powerful zero-shot generalization capabilities for extremely challenging tasks. Project page: urlhttps://github.com/luomingshuang/M3GPT.