# MotionGPT3: Human Motion as a Second Modality

arXiv: https://arxiv.org/abs/2506.24086 · HTML: https://mlsanity.com/paper/2506.24086/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 80 of its 97 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 30 of 80)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [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)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)

## Built on by (most cited first, 30 of 37)

- [TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control](https://mlsanity.com/paper/2602.07439/) (2026)
- [LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens](https://mlsanity.com/paper/2602.12370/) (2026)
- [IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation](https://mlsanity.com/paper/2512.10730/) (2025)
- [ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body](https://mlsanity.com/paper/2512.14234/) (2025)
- [SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation](https://mlsanity.com/paper/2601.00590/) (2026)
- [ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning](https://mlsanity.com/paper/2603.13500/) (2026)
- [SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control](https://mlsanity.com/paper/2605.22894/) (2026)
- [SMooGPT: Stylized Motion Generation using Large Language Models](https://mlsanity.com/paper/2509.04058/) (2025)
- [NECromancer: Breathing Life into Skeletons via BVH Animation](https://mlsanity.com/paper/2602.06548/) (2026)
- [UniHM: Unified Dexterous Hand Manipulation with Vision Language Model](https://mlsanity.com/paper/2603.00732/) (2026)
- [PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition](https://mlsanity.com/paper/2603.08590/) (2026)
- [ViHOI: Human-Object Interaction Synthesis with Visual Priors](https://mlsanity.com/paper/2603.24383/) (2026)
- [UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Framework](https://mlsanity.com/paper/2512.03918/) (2025)
- [MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation](https://mlsanity.com/paper/2512.13840/) (2025)
- [Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs](https://mlsanity.com/paper/2604.21926/) (2026)
- [MotionVLA: Vision-Language-Action Model for Humanoid Motion](https://mlsanity.com/paper/2606.15142/) (2026)
- [Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation](https://mlsanity.com/paper/2602.02401/) (2026)
- [From Diffusion to Flow: Efficient Motion Generation in MotionGPT3](https://mlsanity.com/paper/2603.26747/) (2026)
- [FlowCoMotion: Text-to-Motion Generation via Token-Latent Flow Modeling](https://mlsanity.com/paper/2604.11083/) (2026)
- [UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars](https://mlsanity.com/paper/2605.14731/) (2026)
- [MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control](https://mlsanity.com/paper/2605.26006/) (2026)
- [MultiAct: Text-to-Motion Generation from Composite Text via Tailored Attention Guidance](https://mlsanity.com/paper/2605.30925/) (2026)
- [Social Structure Matters in 3D Human-Human Interaction Generation](https://mlsanity.com/paper/2606.24255/) (2026)
- [MRBench: A Comprehensive Benchmark for Human Motion-Text Retrieval](https://mlsanity.com/paper/2608.07993/) (2026)
- [SeMoCo: A Semantic-First Motion Codec for Motion Language Modeling](https://mlsanity.com/paper/2608.24334/) (2026)
- [Negation Beyond the Verbal Channel: Temporal Multimodal Correlates in Dialogue](https://mlsanity.com/paper/2609.16396/) (2026)
- [GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models](https://mlsanity.com/paper/2601.07632/) (2026)
- [Unified Number-Free Text-to-Motion Generation Via Flow Matching](https://mlsanity.com/paper/2603.27040/) (2026)
- [Encoder-Free Human Motion Understanding via Structured Motion Descriptions](https://mlsanity.com/paper/2604.21668/) (2026)
- [MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning](https://mlsanity.com/paper/2606.23061/) (2026)

## Abstract (arXiv)

With the rapid progress of large language models (LLMs), multimodal frameworks that unify understanding and generation have become promising, yet they face increasing complexity as the number of modalities and tasks grows. We observe that motion quantization introduces approximation errors that cap motion quality, and that unifying discrete text and continuous motion within a single-stream backbone amplifies cross-modal interference. Motivated by recent multi-branch Transformer designs that separate signals from different modalities, we propose MotionGPT3, a bimodal motion-language model for both understanding and generation. MotionGPT3 encodes raw motion into a continuous latent space using a variational autoencoder (VAE), thereby avoiding quantization-induced artifacts, while leveraging the semantic prior of pretrained language models. A dual-stream Transformer with shared attention preserves modality-specific routes while enabling controlled, bidirectional information flow, which reduces interference, stabilizing optimization, and empirically accelerates convergence without degrading fidelity. For multimodal joint training, a generate-then-align three-stage schedule further improves stability and limits cross-task interference. Experiments show that MotionGPT3 achieves 2x faster convergence in training loss and up to 4x faster convergence in validation, while maintaining state-of-the-art performance on standard motion understanding and motion generation benchmarks.