FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies 文章

ArXiv CS.AI2026-05-27NEWSen作者: Xintong Hu, Xuhong Huang, Jinyu Zhang, Yutong Yao, Yuchong Sun, Qiuyue Wang, Mingsheng Li, Sicheng Xie, Yitao Liu, Junhao Chen, Yixuan Chen, Yingming Zheng, Shuai Bai, Tao Yu
查看原文 →
关系图谱

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies · 相关技术

相关技术

ODE远程代码执行（RCE）execdivide-and-conquer partitioningalignmentVision-Language-Action (VLA) modelsVQAVLAUCTTEEStraight-Through EstimatorStanScalaRoboticsReferring expression comprehension (REC)PPROTAMITVLMHISForFOLANN