dreamdifferent/panda-widowx-level4-l4video200-fix-v2-action-decoder-iter900

VAM-Cross MimicVideo World2Action decoder

This public repository contains the World2Action decoder checkpoint from iteration 900 of w2a_panda_widowx_level4_l4video200_fix_v2_action_iter2374_videolora_iter200_widowx_teleop_recording_frame_v1. The run stopped because of unknown. 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-video-fused@f0cea76b62c5dd66b06b9f965932ddea32a7b546
• Initial action decoder: dreamdifferent/vam-cross-target-widowx250-native-2cam-action-decoder@93750cccda01620e3c028477e4c49bc5c996a68d
• Frozen Video LoRA: dreamdifferent/vam-cross-level4-panda-widowx-widowx-texture-video-lora-iter200@42a02cb2f7f1ea7008e0193e97f7e0a2ba977163

Action and data contract

• Dataset: dreamdifferent/vam-cross-level4-panda-widowx-widowx-texture@334af5330c91d71d78e944607e4c61d7e2ba6cd2
• Episodes/frames: 163 / 54200
• Cameras: observation.images.corner_cam, observation.images.front_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.