| Motion Anything: Any to Motion Generation | ✓ Link | 0.028 | 0.829 | 9.521 | 2.705 | Motion Anything | 2025-03-10 |
| Not All Frames Are Equal: Complexity-Aware Masked Motion Generation via Motion Spectral Descriptors | | 0.028 | 0.814 | 9.73 | 1.311 | DynMask | 2026-03-31 |
| Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer | ✓ Link | 0.029 | | | | MoTok-DDM-4 | 2026-03-19 |
| BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis | | 0.030 | 0.809 | 9.556 | 1.374 | BiPO | 2024-11-28 |
| MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model | | 0.030 | 0.842 | 9.575 | 1.714 | MotionPCM | 2025-01-31 |
| MoScale: Autoregressive Next-Scale Prediction for Human Motion Generation and Editing | ✓ Link | 0.03 | 0.856 | | 1.105 | ScaleMoGen | 2026-09-08 |
| DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding | | 0.032 | 0.809 | | 1.288 | DisCoRD (+MoMask) | 2024-11-29 |
| Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation | | 0.032 | 0.839 | 9.487 | 1.142 | RAM | 2026-01-21 |
| LaxMotion: Rethinking Supervision Granularity for 3D Human Motion Generation | | 0.034 | 0.812 | 9.519 | | LaxMotion (3D Finetune) | 2025-11-14 |
| Rethinking Fixed Temporal Grids: Frequency-Disentangled Motion Generation | | 0.040 | | | | FreqMo | 2026-10-02 |
| Multi-level Causal LLM-based Text-to-Motion Generation with Human Alignment | | 0.041 | 0.808 | 9.659 | | MoTiGA (Llama) | 2026-06-03 |
| K-Mask: Kinematic-Aware Masked Modeling for Controllable Text-to-Motion Synthesis | | 0.041 | 0.824 | 9.671 | 1.415 | K-Mask | 2026-09-08 |
| ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation | ✓ Link | 0.042 | 0.813 | 9.472 | 1.243 | ReMoMask-2 | 2026-09-08 |
| Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching | | 0.043 | | | | RMG | 2026-03-16 |
| Rethinking Fixed Temporal Grids: Frequency-Disentangled Motion Generation | | 0.043 | | | | FreqMo-Diff | 2026-10-02 |
| MoMask: Generative Masked Modeling of 3D Human Motions | ✓ Link | 0.045 | 0.807 | | 1.241 | MoMask | 2023-11-29 |
| BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation | ✓ Link | 0.049 | 0.800 | 9.688 | 1.119 | BAD (CBS) | 2024-09-17 |
| Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss | ✓ Link | 0.051 | 0.803 | 9.480 | | Free-T2M (StableMoFusion) | 2025-01-30 |
| MCM: Multi-condition Motion Synthesis Framework | ✓ Link | 0.053 | 0.788 | 9.585 | 0.8104 | MCM | 2024-04-19 |
| BAMM: Bidirectional Autoregressive Motion Model | ✓ Link | 0.055 | 0.814 | 9.717 | 1.687 | BAMM | 2024-03-28 |
| Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model | | 0.056 | 0.821 | | | Being-M0.5-PRQ 4 | 2025-08-11 |
| Towards Interactive Intelligence for Digital Humans | | 0.057 | | | | FloodDiffusion | 2025-12-15 |
| Language-Guided Transformer Tokenizer for Human Motion Generation | | 0.057 | 0.83 | | 1.54 | LG-Tok | 2026-02-09 |
| BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation | ✓ Link | 0.065 | 0.808 | 9.694 | 1.194 | BAD (OAAS) | 2024-09-17 |
| Temporal Consistency-Aware Text-to-Motion Generation | ✓ Link | 0.068 | | | | TCaS-VQ-VAE | 2026-02-20 |
| Causal Motion Diffusion Models for Autoregressive Motion Generation | | 0.068 | 0.86 | | | CMDM w/ FSS | 2026-02-26 |
| BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion | | 0.069 | 0.841 | 9.524 | | BiMoGen | 2026-09-28 |
| DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion | | 0.070 | 0.783 | 9.551 | 2.062 | DiverseMotion (s=1) | 2023-09-04 |
| MotionVLA: Vision-Language-Action Model for Humanoid Motion | ✓ Link | 0.071 | | 9.548 | | MotionVLA (Qwen3.5-2B) | 2026-06-13 |
| DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion | | 0.072 | 0.802 | 9.683 | 1.869 | DiverseMotion (s=2) | 2023-09-04 |
| Learn to Modify: Self-evolving Multi-agent Refinement Framework for Conversational Text-to-Motion Generation | | 0.075 | 0.827 | 9.277 | | SMART | 2026-10-20 |
| MMM: Generative Masked Motion Model | ✓ Link | 0.080 | 0.794 | 9.411 | 1.164 | MMM (predict length) | 2023-12-06 |
| MUGEN: A Unified Framework for Efficient Motion Understanding and Generation | | 0.087 | 0.859 | 9.510 | 0.83 | MUGEN | 2026-07-30 |
| MMM: Generative Masked Motion Model | ✓ Link | 0.089 | 0.804 | 9.577 | 1.226 | MMM (gt length) | 2023-12-06 |
| ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model | ✓ Link | 0.103 | 0.795 | 9.018 | 1.795 | ReMoDiffuse | 2023-04-03 |
| Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion | | 0.103 | 0.805 | 9.672 | | Odoriko | 2026-06-19 |
| DrawMotion: Generating 3D Human Motions by Freehand Drawing | ✓ Link | 0.108 | | | | DrawMotion | 2026-05-20 |
| GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation | ✓ Link | 0.109 | 0.787 | 9.826 | 2.430 | GUESS | 2024-01-04 |
| ParCo: Part-Coordinating Text-to-Motion Synthesis | ✓ Link | 0.109 | 0.801 | 9.576 | 1.382 | ParCo | 2024-03-27 |
| AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism | ✓ Link | 0.112 | 0.786 | 9.700 | 2.452 | AttT2M | 2023-09-02 |
| EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation | ✓ Link | 0.112 | 0.786 | 9.551 | 1.641 | EMDM | 2023-12-04 |
| T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations | ✓ Link | 0.116 | 0.775 | 9.761 | 1.856 | T2M-GPT (τ = 0.5) | 2023-01-15 |
| Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs | ✓ Link | 0.116 | 0.785 | 9.692 | 2.766 | GraphMotion | 2023-09-21 |
| T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations | ✓ Link | 0.140 | 0.685 | 9.844 | 3.285 | T2M-GPT (τ = 0) | 2023-01-15 |
| T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations | ✓ Link | 0.141 | 0.775 | 9.722 | 1.831 | T2M-GPT (τ ∈ U[0, 1]) | 2023-01-15 |
| Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model | | 0.141 | 0.815 | | | Being-M0.5-VQ 1 | 2025-08-11 |
| FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing | ✓ Link | 0.151 | 0.784 | 9.263 | 2.696 | FineMoGen | 2023-12-22 |
| Practice Makes Perfect: From Explicit Decomposition to Reinforced Latent Planning in Text-to-Human Motion | ✓ Link | 0.167 | 0.873 | 9.507 | | LaCT-Motion | 2026-09-08 |
| AvatarGPT: All-in-One Framework for Motion Understanding Planning Generation and Beyond | ✓ Link | 0.168 | 0.796 | 9.624 | | AvatarGPT (T5-Large) | 2023-11-28 |
| UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation | | 0.194 | 0.841 | 9.583 | | UniMotion (Gen. & Und.) | 2026-03-23 |
| MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation | ✓ Link | 0.203 | 0.821 | 9.701 | 2.702 | MoRL | 2026-02-16 |
| MotionGPT3: Human Motion as a Second Modality | ✓ Link | 0.208 | 0.837 | 9.700 | 1.018 | MotionGPT3 (Gen. & Und.) | 2025-06-30 |
| UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation | | 0.231 | 0.830 | 9.649 | | UniMotion (Gen. only) | 2026-03-23 |
| MotionGPT3: Human Motion as a Second Modality | ✓ Link | 0.239 | 0.826 | 9.688 | 1.560 | MotionGPT3 (Gen. only) | 2025-06-30 |
| Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model | | 0.243 | 0.783 | 9.278 | 1.614 | Fg-T2M | 2023-09-12 |
| Motion Mamba: Efficient and Long Sequence Motion Generation | ✓ Link | 0.281 | 0.792 | 9.871 | 2.294 | Motion Mamba | 2024-03-12 |
| MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model | ✓ Link | 0.304 | 0.798 | 9.607 | 2.259 | MotionLCM (4-step) | 2024-04-30 |
| OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers | | 0.381 | 0.784 | 9.657 | | OMG | 2023-12-14 |
| Executing your Commands via Motion Diffusion in Latent Space | ✓ Link | 0.473 | 0.772 | 9.724 | 2.413 | MLD | 2022-12-08 |
| Human Motion Diffusion Model | ✓ Link | 0.544 | 0.611 | 9.559 | 2.799 | MDM | 2022-09-29 |
| MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model | ✓ Link | 0.630 | 0.782 | 9.410 | 1.553 | MotionDiffuse | 2022-08-31 |
| Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation | | 0.774 | 0.676 | 8.23 | | MAA | 2023-05-16 |
| TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration | ✓ Link | 1.021 | | 9.513 | 4.139 | TM2D (t2m) | 2023-04-05 |
| Generating Diverse and Natural 3D Human Motions From Text | ✓ Link | 1.087 | 0.736 | 9.175 | 2.219 | T2M | 2022-01-01 |
| Plan, Don't Pose: Long Composite Motion Generation with Text-Aligned BFM | | 1.172 | 0.876 | | 1.233 | Text2BFM | 2026-05-28 |
| TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts | ✓ Link | 1.501 | 0.729 | 8.589 | 2.424 | TM2T | 2022-07-04 |
| TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts | ✓ Link | 5.012 | 0.345 | 6.409 | | Text2Gesture | 2022-07-04 |
| Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model | | 10.21 | 0.735 | 23.692 | | Diffuion Motion | 2022-10-22 |
| TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts | ✓ Link | 11.02 | 0.486 | 7.676 | | Language2Pose | 2022-07-04 |
| Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer | ✓ Link | | 0.799 | | | MoTok-DDM-2 | 2026-03-19 |
| SFM: Taming State Space Models for Text-to-Motion via Spatial-Frequency Modeling | | | 0.845 | | | SFM | 2026-09-08 |