Duplicate from yufanwei/CD-LAM

.gitattributes

@@ -0,0 +1,4 @@
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text

NOTICE

@@ -0,0 +1,14 @@
+CD-LAM
+Copyright 2026 CD-LAM contributors
+
+The checkpoint files are derivatives of an NVIDIA model. The complete
+applicable NVIDIA Open Model License Agreement is included in
+LICENSE.pdf.
+
+Licensed by NVIDIA Corporation under the NVIDIA Open Model License
+
+Built on NVIDIA Cosmos
+
+The release does not redistribute the external NVIDIA base checkpoint,
+datasets, SAM3, or CoWTracker. Those components retain their own terms; see
+the model card and asset_manifest.json.

README.md

@@ -0,0 +1,60 @@
+---
+license: other
+license_name: nvidia-open-model-license
+license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
+library_name: pytorch
+tags:
+  - latent-action-model
+  - world-model
+  - robotics
+  - video-prediction
+  - research
+---
+
+# CD-LAM
+
+This repository contains three CD-LAM model entries.
+
+| entry | file | role |
+|---|---|---|
+| LAM | `models/lam/model.pt` | 32D latent-action model |
+| Pretrain | `models/pretrain/model.pt` | latent-action-conditioned world-model overlay |
+| Posttrain | `models/posttrain/model.pt` | robot-action post-trained world-model overlay |
+
+The posttrain folder also contains its required
+`models/posttrain/bridge.pt` and
+`models/posttrain/action_contract.json`. They are support files for the
+posttrain entry, not additional models.
+
+## Use with the source release
+
+```bash
+git clone https://github.com/yufanwei/CD-LAM.git
+cd CD-LAM
+bash setup.sh --accept-base-license --with-models
+```
+
+The source downloader pins an immutable Hub revision and verifies file sizes
+and SHA-256 values from `asset_manifest.json`.
+
+## Compatibility
+
+The LAM and pretrain entries are compatible with each other. The posttrain
+entry must use the bridge and action contract in the same folder.
+
+The two world-model files are overlays and require the compatible external
+NVIDIA 2B base checkpoint, Cosmos tokenizer, and text encoder. Exact revisions
+are recorded in `asset_manifest.json` and the
+[CD-LAM source release](https://github.com/yufanwei/CD-LAM).
+
+## Scope
+
+These are inference and evaluation research artifacts, not optimizer-resume
+checkpoints, a robot policy, or a safety controller. Model identity and tensor
+verification do not by themselves reproduce the manuscript tables.
+
+## License and citation
+
+Read `NOTICE` and `LICENSE.pdf` before using the checkpoints. Built on NVIDIA Cosmos.
+The paper BibTeX entry is available in the source repository's
+[README](https://github.com/yufanwei/CD-LAM#citation).

models/lam/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084f9b1ad1e09926c217a0fe7668e672f2e93b89314a4ff18eeed20b6b5cb6ee
+size 2839525895

models/posttrain/action_contract.json

@@ -0,0 +1,30 @@
+{
+  "schema_version": 1,
+  "contract_id": "agibot-alpha-22d-raw-adjacent-stride4",
+  "embodiment": "agibot",
+  "action_dim": 22,
+  "action_tokens": 12,
+  "block_size": 4,
+  "source_stride": 4,
+  "loader_representation": "minmax_normalized_block_anchor_cumulative_delta",
+  "bridge_representation": "raw_adjacent_stride_delta",
+  "stats_relative_path": "shared_meta/AgiBot_stats.json",
+  "stats_sha256": "ea3999b4141236cf41c702b6c618bc6ab9ee696a80f154eaa91efbbf88fbd72b",
+  "modality_relative_path": "shared_meta/AgiBot_modality.json",
+  "modality_sha256": "29fd7cec495ddeb0baa8e6d13c3d73a259a1bb2447b7afb5fe2390f1e223a4ed",
+  "metadata_source_repository": "https://github.com/NVIDIA/DreamDojo.git",
+  "metadata_source_revision": "02f119b759d5c7f84a399fdeea3c6e82e7ed6cff",
+  "legacy_bridge_sha256_by_scale_family": {
+    "posttrain": "346710032ca50ba18876d2727981b18db60cb9e7bea1d6efdb10056bb7232fdd"
+  },
+  "layout": [
+    {"name": "left_arm_joint_position", "start": 0, "end": 7},
+    {"name": "right_arm_joint_position", "start": 7, "end": 14},
+    {"name": "left_effector_position", "start": 14, "end": 15},
+    {"name": "right_effector_position", "start": 15, "end": 16},
+    {"name": "head_position", "start": 16, "end": 18},
+    {"name": "waist_pitch", "start": 18, "end": 19},
+    {"name": "waist_lift", "start": 19, "end": 20},
+    {"name": "robot_velocity", "start": 20, "end": 22}
+  ]
+}

models/posttrain/bridge.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ab4ed2fe755d7e4fb127ef8f0e9d05feda859855d05f4509797f1bae301e8a
+size 639927

models/posttrain/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07440025c3780f907fb2b87c27263343b02e2464f3be658f07543aada088d86c
+size 4303229324

models/pretrain/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b06cebedc3fadc64b4795bd3730b29c794ba8bf38a237c5bf19e1e3aca74b9c
+size 4303229324