Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement 文章

ArXiv CS.CV2026-05-26NEWSen作者: Weikang Qiu, Huashuo Lei, Tinglin Huang, Rex Ying
查看原文 →
关系图谱

Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement · 相关技术

相关技术

Vision-Language-Action ModelORMTTEODEPLAlanguage model研究法辛烷值divide-and-conquer partitioningattentionVision-Language-Action (VLA) modelsVLAUCTTokenSynthetic Aperture RadarReferring expression comprehension (REC)Parts-of-Speech (POS) tagsNarrative Abstraction BenchmarkNPUMITVLMICTHISForFFIENADiTAutomatic Domain RandomizationARGANNANGLE