Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Paper • 2608.27550 • Published • 85
VLAct
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
-
-
StarVLA/VLAct_Qwen3_Pretrain
Robotics • Updated • 19 • 6 -
StarVLA/VLAct-Qwen3VL4B-OFT-RoboDojo
Robotics • Updated • 23 -
StarVLA/VLAct_Qwen3OFT_Robotwin_Finetune
Robotics • Updated • 23 -
StarVLA/VLAct_Qwen3OFT_Robotwin_all_Finetune
Robotics • Updated • 22 -
StarVLA/VLAct_Qwen3PI_Robotwin_Finetune
Robotics • Updated • 25 -
StarVLA/VLAct_Qwen3PI_Robotwin_all_Finetune
Robotics • Updated • 26 -
StarVLA/VLAct_Qwen3GR00T_Robotwin_Finetune
Robotics • Updated • 20 -
StarVLA/VLAct_Qwen3GR00T_Robotwin_all_Finetune
Robotics • Updated • 10 -
StarVLA/VLAct_Qwen3PI_Libero_Plus_Finetune
Robotics • Updated • 24 -
StarVLA/VLAct_Qwen3OFT_Domino_Finetune
Robotics • Updated • 21 -
StarVLA/VLAct_Qwen3PI_VLA_Arena_Finetune
Robotics • Updated • 25