Cover Image

ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lu, Shunlin, Wang, Jingbo, Lu, Zeyu, Chen, Ling-Hao, Dai, Wenxun, Dong, Junting, Dou, Zhiyang, Dai, Bo, Zhang, Ruimao
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing
by: Chen, Ling-Hao, et al.
Published: (2024)

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data
by: Fan, Ke, et al.
Published: (2025)

MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model
by: Dai, Wenxun, et al.
Published: (2024)

MotionLLM: Understanding Human Behaviors from Human Motions and Videos
by: Chen, Ling-Hao, et al.
Published: (2024)

ARMO: Autoregressive Rigging for Multi-Category Objects
by: Sun, Mingze, et al.
Published: (2025)

MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space
by: Xiao, Lixing, et al.
Published: (2025)

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
by: Lin, Jing, et al.
Published: (2023)

Towards Synthesized and Editable Motion In-Betweening Through Part-Wise Phase Representation
by: Dai, Minyue, et al.
Published: (2025)

Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset
by: Zhang, Yuhong, et al.
Published: (2025)

Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models
by: Huang, Yuzhou, et al.
Published: (2024)

Motion2Motion: Cross-topology Motion Transfer with Sparse Correspondence
by: Chen, Ling-Hao, et al.
Published: (2025)

Controllable Text-to-Motion Generation via Modular Body-Part Phase Control
by: Dai, Minyue, et al.
Published: (2026)

MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning
by: Feng, Yuming, et al.
Published: (2024)

TELA: Text to Layer-wise 3D Clothed Human Generation
by: Dong, Junting, et al.
Published: (2024)

Scaling Laws For Diffusion Transformers
by: Liang, Zhengyang, et al.
Published: (2024)

ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation
by: Hwang, Inwoo, et al.
Published: (2026)

EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation
by: Zhou, Wenyang, et al.
Published: (2023)

CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos
by: Zhao, Chengfeng, et al.
Published: (2026)

MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds
by: Lei, Jiahui, et al.
Published: (2024)

GAS: Generative Avatar Synthesis from a Single Image
by: Lu, Yixing, et al.
Published: (2025)

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
by: Pan, Liang, et al.
Published: (2025)

MoSa: Motion Generation with Scalable Autoregressive Modeling
by: Liu, Mengyuan, et al.
Published: (2025)

ReMoMask: Retrieval-Augmented Masked Motion Generation
by: Li, Zhengdao, et al.
Published: (2025)

MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation
by: Wang, Hongpeng, et al.
Published: (2026)

SemGrasp: Semantic Grasp Generation via Language Aligned Discretization
by: Li, Kailin, et al.
Published: (2024)

FreSca: Scaling in Frequency Space Enhances Diffusion Models
by: Huang, Chao, et al.
Published: (2025)

Dynamic Realms: 4D Content Analysis, Recovery and Generation with Geometric, Topological and Physical Priors
by: Dou, Zhiyang
Published: (2024)

SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation
by: Wang, Yiling, et al.
Published: (2026)

Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes
by: Jiang, Lihan, et al.
Published: (2024)

PALUM: Part-based Attention Learning for Unified Motion Retargeting
by: Liu, Siqi, et al.
Published: (2026)

LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens
by: Li, Zekun, et al.
Published: (2026)

PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction
by: Meng, Ziqiao, et al.
Published: (2025)

DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters
by: Sun, Mingze, et al.
Published: (2024)

Next-Scale Autoregressive Models for Text-to-Motion Generation
by: Zheng, Zhiwei, et al.
Published: (2026)

PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction
by: Meng, Ziqiao, et al.
Published: (2025)

OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression
by: Li, Zhe, et al.
Published: (2025)

LOGO: A Long-Form Video Dataset for Group Action Quality Assessment
by: Zhang, Shiyi, et al.
Published: (2024)

MOSPA: Human Motion Generation Driven by Spatial Audio
by: Xu, Shuyang, et al.
Published: (2025)

InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
by: Wang, Zhenzhi, et al.
Published: (2023)

AR-RAG: Autoregressive Retrieval Augmentation for Image Generation
by: Qi, Jingyuan, et al.
Published: (2025)