T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences 文章

ArXiv CS.CV2026-06-08NEWSen作者: Taeryung Lee, Fabien Baradel, Thomas Lucas, Kyoung Mu Lee, Gregory Rogez
大语言模型
查看原文 →
关系图谱

T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences · 相关技术

相关技术

VQVAETransformer-based Text Encodertransformers1D-convolutional VQVAET2LM