- 🗂️ Repository Layout
- ⚙️ Environment
- 📦 Model Assets & Checkpoints
- 🧩 Data Preparation
- 🚀 Training
- 🧪 RoboTwin Evaluation
- 🧪 LIBERO Evaluation
- 📌 Citation
- 🙏 Acknowledgements
- 📄 License
InternW0 is a physical world-action model with a slow Wan2.2 VideoDiT planner and a fast chunked ActionDiT executor. The video expert produces reusable future context; observation-conditioned routing adapts its layerwise K/V to each new chunk observation, so the model can predict slowly and act quickly.
This repository contains:
- multi-domain soft-prompt/domain-bank pretraining;
- DINOv3 observation encoding and IDM video/action training;
- RoboTwin and LIBERO posttraining readers;
- RoboTwin and LIBERO closed-loop evaluation adapters;
- focused implementation-contract and distributed tests.
Pretraining and posttraining use the same native .pt checkpoint contract.
Force/tactile, real-robot, and laboratory assets described in the paper are not
included here.
InternW0/
├── configs/
│ ├── data/ Dataset and domain-registry configurations
│ ├── model/ W0 DINO/IDM model configuration
│ ├── pretrain.yaml Multi-domain pretraining entry point
│ ├── posttrain_*.yaml RoboTwin/LIBERO posttraining entry points
│ ├── eval_*.yaml RoboTwin/LIBERO evaluation entry points
│ └── train.yaml Base Hydra training graph
├── scripts/
│ ├── train.py Hydra training entry point
│ ├── train_zero1.sh ZeRO-1 launcher
│ ├── train_zero2.sh ZeRO-2 launcher
│ ├── prepare_* Statistics, data, and checkpoint preparation
│ └── run_libero_eval.sh Two-process LIBERO evaluation launcher
├── experiments/
│ ├── robotwin/ RoboTwin policy adapter and evaluation entries
│ └── libero/ LIBERO policy server, client, and adapter
├── src/w0/
│ ├── datasets/ Native readers, normalization, and temporal masks
│ ├── models/wan22/ Wan, W0, ActionDiT, DINO, OVCR, and banks
│ ├── runtime.py Model/data construction and training entry
│ └── trainer.py Distributed trainer and checkpoint lifecycle
├── tests/ Contract and distributed regression tests
├── docs/ Reproduction and architecture documentation
└── assets/ README figures
Python 3.10 is required.
conda create -n w0 python=3.10 -y
conda activate w0
pip install -U pip setuptools wheel
pip install torch==2.7.1 torchvision==0.22.1 \
--extra-index-url https://download.pytorch.org/whl/cu128
pip install -e .
conda install -c conda-forge ffmpeg -yThe Python package is imported as w0.
RoboTwin and LIBERO are external simulation dependencies and are not installed by this package.
InternW0 does not bundle model weights, datasets, or trained checkpoints. Use explicit local paths or the environment variables below.
| Asset | Purpose | Environment variable |
|---|---|---|
| Wan2.2 TI2V-5B model directory | VideoDiT, VAE, tokenizer, and text encoder | W0_WAN_MODEL_DIR |
| DINOv3 ViT-B/16 | Future/IDM observation encoder | W0_DINO_WEIGHTS |
| InternW0 checkpoints | Base, RoboTwin-clean, and LIBERO .pt weights |
W0_BASE_CHECKPOINT, W0_ROBOTWIN_CHECKPOINT, or W0_LIBERO_CHECKPOINT |
| RoboTwin dataset | Joint-space posttraining and evaluation | W0_ROBOTWIN_DATA |
| LIBERO dataset | Native 20 Hz EEF10 posttraining | W0_LIBERO_DATA |
| LIBERO checkout | Closed-loop LIBERO environment | LIBERO_PATH |
| RoboTwin checkout | Closed-loop RoboTwin environment | EVALUATION.robotwin_root |
A convenient local layout is:
assets/
wan22/
dinov3-vitb16-pretrain-lvd1689m/
checkpoints/
base.pt
robotwin-clean.pt
libero.pt
data/
robotwin/
libero/
external/
RoboTwin/
LIBERO/
outputs/
All released InternW0 checkpoints are available in the InternW0 Hugging Face collection.
| Asset | Hugging Face URL |
|---|---|
| InternW0 base | InternRobotics/InternW0-Base |
| InternW0 RoboTwin-clean | InternRobotics/InternW0-RoboTwin-clean |
| InternW0 LIBERO | InternRobotics/InternW0-Libero |
Download the canonical .pt files rather than the auto-generated
pytorch_model.bin copies. For example:
hf download InternRobotics/InternW0-Base \ InternW0-Base.pt InternW0-Base.transfer.json normalization.json \ --local-dir checkpoints/base hf download InternRobotics/InternW0-RoboTwin-clean \ InternW0-RoboTwin-clean.pt normalization.json \ checkpoint_metadata.json posttrain_config.yaml \ --local-dir checkpoints/robotwin-clean hf download InternRobotics/InternW0-Libero \ InternW0-Libero.pt normalization.json \ checkpoint_metadata.json posttrain_config.yaml \ --local-dir checkpoints/libero
Pass the resulting paths through the environment variables below. Do not commit model files to this repository.
First precompute UMT5 text embeddings from the LeRobot task metadata, then build train-only q01/q99 command/statistics:
W0_ROBOTWIN_DATA="$W0_ROBOTWIN_DATA" \ python scripts/precompute_text_embeds.py \ --config-name posttrain_robotwin python scripts/prepare_robotwin_stats.py \ --dataset-root "$W0_ROBOTWIN_DATA" \ --output assets/robotwin/normalization.json
The retained best-practice recipe uses the clean export, 25 Hz sampling
(sampling_stride=2), all valid windows, ColorJitter, and offset 0 for
Clean2Random. Actions and proprio are scattered into 37D slots:
[0, 1, 2, 3, 4, 5, 16, 17, 18, 19, 20, 21, 22, 33]
First precompute UMT5 text embeddings, then build train-only statistics:
python scripts/prepare_libero_text_embeds.py \ --dataset-root "$W0_LIBERO_DATA" \ --cache-dir assets/libero/text_embeds_cache python scripts/prepare_libero_posttrain.py \ --dataset-root "$W0_LIBERO_DATA" \ --output assets/libero/normalization.json
LIBERO remains at native 20 Hz. Its EEF10 representation occupies:
[7, 8, 9, 10, 11, 12, 13, 14, 15, 16]
The reference registry is:
configs/data/domain_banks/internw0_domains.json
It preserves domain identity, source ordering, native fields, and camera slots. For a local copy of the source datasets, regenerate it:
python scripts/build_action_domain_registry.py \ --roots external/InternData-A1 external/RoboMIND2 \ --output configs/data/domain_banks/internw0_domains.json
Regenerate domain statistics after changing the registry because its fingerprint is part of the data contract:
python scripts/prepare_domain_statistics.py \ --registry configs/data/domain_banks/internw0_domains.json \ --output assets/domain_data/pretrain_stats.json
InternW0 uses Hydra. init_checkpoint loads model weights only and starts a new
optimizer; resume restores a complete compatible training state. The two
modes are mutually exclusive.
export W0_DOMAIN_STATS=assets/domain_data/pretrain_stats.json export W0_DOMAIN_TEXT_CACHE=assets/domain_data/text_embeds bash scripts/train_zero2.sh 8 \ --config-name pretrain \ output_dir=outputs/pretrain
The task uses K=8 prompts, 11 reference domains, DINOv3 B/16 observations, IDM training, H=64, C=16, and no action history.
Best Clean2Random recipe:
export W0_ROBOTWIN_DATA=data/robotwin export W0_ROBOTWIN_STATS=assets/robotwin/normalization.json export W0_ROBOTWIN_CHECKPOINT=checkpoints/robotwin-clean.pt export W0_WAN_MODEL_DIR=assets/wan22 export W0_DINO_WEIGHTS=assets/dinov3-vitb16-pretrain-lvd1689m bash scripts/train_zero1.sh 8 \ --config-name posttrain_robotwin
The config already uses offset 0. Other offsets can be studied with explicit Hydra overrides.
export W0_LIBERO_DATA=data/libero export W0_LIBERO_STATS=assets/libero/normalization.json export W0_LIBERO_CHECKPOINT=checkpoints/libero.pt export W0_LIBERO_TEXT_CACHE=assets/libero/text_embeds_cache export W0_WAN_MODEL_DIR=assets/wan22 export W0_DINO_WEIGHTS=assets/dinov3-vitb16-pretrain-lvd1689m bash scripts/train_zero1.sh 8 \ --config-name posttrain_libero
Use an external RoboTwin checkout:
python experiments/robotwin/eval_robotwin_single.py \ EVALUATION.robotwin_root=external/RoboTwin \ EVALUATION.task_name=<task> \ EVALUATION.ckpt=<checkpoint.pt>
The adapter applies the same camera canvas, action slots, normalization, and fixed control clock used by the posttraining reader. See Evaluation for the full protocol.
| Setting | Clean | Randomized | Average |
|---|---|---|---|
| Full | 93.20 | 93.04 | 93.12 |
| Clean2Random | 83.20 | 68.00 | 75.60 |
Full jointly uses clean and randomized demonstrations. Clean2Random trains only on clean demonstrations and evaluates transfer to unseen randomized scenes. These paper-reported numbers are not rerun as part of code-release validation.
The launcher starts a W0 policy server and a separate LIBERO environment client:
export CKPT=checkpoints/libero.pt export W0_WAN_MODEL_DIR=assets/wan22 export W0_LIBERO_STATS=assets/libero/normalization.json export W0_LIBERO_TEXT_CACHE=assets/libero/text_embeds_cache export LIBERO_PATH=external/LIBERO SUITE=libero_goal TASK_ID=0 NUM_TRIALS=50 \ bash scripts/run_libero_eval.sh
The default protocol executes a complete 16-action chunk unless
EXECUTE_N_ACTIONS is explicitly overridden. Changing that value changes the
closed-loop protocol and is not equivalent to training a chunk-8 model.
InternW0 covers all 40 tasks in the four official LIBERO suites.
| Spatial | Object | Goal | Long | Average |
|---|---|---|---|---|
| 99.4 | 99.4 | 98.6 | 97.0 | 98.6 |
These paper-reported numbers are not rerun as part of code-release validation.
If you find InternW0 useful, please cite:
@article{internw0, title = {InternW0: A Foundational Physical World Model for Efficient Real-World Interactions}, author = {Jisong Cai and Yao Mu and Ganlin Yang and Zhe Cao and Zhangzheng Tu and Xing Gao and Kailin Li and Xinyu Zhan and Lixin Yang and Yangkun Zhu and Haoxiang Ma and Ming Zhou and Qiaojun Yu and Yufei Xue and Liqun He and Yifei Yao and Yifan Zhu and Long Ling and Bingqi Jiang and Haoyu Guo and Xueyue Zhu and Bowen Zhou and Bin Zhao and Tianfan Xue and Chunhua Shen and Weinan Zhang}, journal = {arXiv preprint arXiv:2609.27656}, year = {2026} }
InternW0 builds on ideas and open-source infrastructure from Wan2.2, DINOv3, RoboTwin, LIBERO, LeRobot. We thank their authors and contributors for releasing useful models, data tools, and evaluation environments.
This repository is released under the MIT License, except for third-party code and assets that retain their original licenses.