dreamdifferent/panda-robosuite-level4-wrist-ablation-v1-videolora200-action-decoder-iter900

VAM-Cross MimicVideo World2Action decoder

This public repository contains the World2Action decoder checkpoint from iteration 900 of w2a_panda_robosuite_level4_2cam_wrist_ablation_v1_action_iter2374_videolora_iter200_widowx_teleop_recording_frame_v1. The run stopped because of completed. The newest complete model, optimizer, scheduler, and trainer checkpoint set was verified before selecting the uploaded model weight.

Required frozen inputs

• —MimicVideo commit: e3355dbc93132b576c02f920a59b4fc18a4f5906
• —Initial Video2World backbone: dreamdifferent/widowx250-wrist-ablation-v1-video-fused@8e39d96344dea0a82ae673874a38206a6c412948
• —Initial action decoder: dreamdifferent/widowx250-wrist-ablation-v1-action-decoder-iter2374@0ea6db91672db019d9d6dc9a6c9bd1ecc0504001
• —Frozen Video LoRA: dreamdifferent/panda-robosuite-level4-wrist-ablation-v1-video-lora-iter200@24e15bdb2250e55e07a4af11f8f5022615362e6b

Action and data contract

• —Dataset: dreamdifferent/vam-cross-level4-panda-robosuite-widowx-texture-corner-wrist@30163462034e94e79eec5890cf10504feed1966e
• —Episodes/frames: 162 / 54352
• —Cameras: observation.images.corner_cam, observation.images.wrist_cam
• —Target: 15 achieved-EE/gripper actions at 5 Hz
• —Pose target: relative_to_current_achieved_pose in widowx_reference_base/teleop_aligned_tool
• —Rotation: rotation_6d

The dataset and frozen inputs are not included. Use the pinned JSON and effective config.yaml included in this repository.