# AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond

arXiv: https://arxiv.org/abs/2311.16468 · HTML: https://mlsanity.com/paper/2311.16468/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 43 references that are in the map.
- First posted on arXiv 28 Nov 2023.

## Builds on (most cited first, 30 of 34)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [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)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (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)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (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)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [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)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [Guided Motion Diffusion for Controllable Human Motion Synthesis](https://mlsanity.com/paper/2305.12577/) (2023)
- [TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis](https://mlsanity.com/paper/2305.00976/) (2023)
- [AdaPlanner: Adaptive Planning from Feedback with Language Models](https://mlsanity.com/paper/2305.16653/) (2023)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)

## Built on by (most cited first, 30 of 63)

- [Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos](https://mlsanity.com/paper/2507.15597/) (2025)
- [MotionLLM: Understanding Human Behaviors from Human Motions and Videos](https://mlsanity.com/paper/2405.20340/) (2024)
- [HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation](https://mlsanity.com/paper/2505.04512/) (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)
- [MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling](https://mlsanity.com/paper/2409.17686/) (2024)
- [Unimotion: Unifying 3D Human Motion Synthesis and Understanding](https://mlsanity.com/paper/2409.15904/) (2024)
- [MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm](https://mlsanity.com/paper/2502.02358/) (2025)
- [EgoLM: Multi-Modal Language Model of Egocentric Motions](https://mlsanity.com/paper/2409.18127/) (2024)
- [Human Motion Video Generation: A Survey](https://mlsanity.com/paper/2509.03883/) (2025)
- [Scaling Large Motion Models with Million-Level Human Motions](https://mlsanity.com/paper/2410.03311/) (2024)
- [Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator](https://mlsanity.com/paper/2411.17799/) (2024)
- [PresentAgent: Multimodal Agent for Presentation Video Generation](https://mlsanity.com/paper/2507.04036/) (2025)
- [ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation](https://mlsanity.com/paper/2503.13130/) (2025)
- [SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters](https://mlsanity.com/paper/2412.00174/) (2024)
- [Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input](https://mlsanity.com/paper/2504.08449/) (2025)
- [Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion](https://mlsanity.com/paper/2404.11375/) (2024)
- [MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations](https://mlsanity.com/paper/2410.13790/) (2024)
- [Human-Centric Foundation Models: Perception, Generation and Agentic Modeling](https://mlsanity.com/paper/2502.08556/) (2025)
- [Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model](https://mlsanity.com/paper/2508.07863/) (2025)
- [FrankenMotion: Part-level Human Motion Generation and Composition](https://mlsanity.com/paper/2601.10909/) (2026)
- [You Think, You ACT: The New Task of Arbitrary Text to Motion Generation](https://mlsanity.com/paper/2404.14745/) (2024)
- [Progressive Human Motion Generation Based on Text and Few Motion Frames](https://mlsanity.com/paper/2503.13300/) (2025)
- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain](https://mlsanity.com/paper/2503.22397/) (2025)
- [RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-Wave Point Cloud Sequence](https://mlsanity.com/paper/2504.09862/) (2025)
- [HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding](https://mlsanity.com/paper/2503.12955/) (2025)
- [FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding](https://mlsanity.com/paper/2504.19514/) (2025)
- [Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion](https://mlsanity.com/paper/2505.11013/) (2025)
- [DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions](https://mlsanity.com/paper/2508.17342/) (2025)

## Abstract (arXiv)

Large Language Models(LLMs) have shown remarkable emergent abilities in unifying almost all (if not every) NLP tasks. In the human motion-related realm, however, researchers still develop siloed models for each task. Inspired by InstuctGPT, and the generalist concept behind Gato, we introduce AvatarGPT, an All-in-One framework for motion understanding, planning, generations as well as other tasks such as motion in-between synthesis. AvatarGPT treats each task as one type of instruction fine-tuned on the shared LLM. All the tasks are seamlessly interconnected with language as the universal interface, constituting a closed-loop within the framework. To achieve this, human motion sequences are first encoded as discrete tokens, which serve as the extended vocabulary of LLM. Then, an unsupervised pipeline to generate natural language descriptions of human action sequences from in-the-wild videos is developed. Finally, all tasks are jointly trained. Extensive experiments show that AvatarGPT achieves SOTA on low-level tasks, and promising results on high-level tasks, demonstrating the effectiveness of our proposed All-in-One framework. Moreover, for the first time, AvatarGPT enables a principled approach by iterative traversal of the tasks within the closed-loop for unlimited long-motion synthesis.