LO-World
Pretrained PyTorch checkpoints for UniAV-World, a BEV latent world model for joint future occupancy and LiDAR prediction.
Download
hf download JimmyLiaoo/LO-World --include "*.pth" --include SHA256SUMS --local-dir ckpts
Checkpoints
| File | Model |
|---|---|
| occ_lidar_vae.pth | Joint occupancy–LiDAR tokenizer |
| bev_world_2f.pth | 2-frame World Model |
| bev_world_6f.pth | 6-frame World Model |
| bev_world_6f_layout.pth | 6-frame World Model with BEVLayout conditioning |
| bev_world_6f_autoregressive.pth | Autoregressive World Model |
| bev_world_12f_layout_autoregressive.pth | 12-frame autoregressive World Model with BEVLayout conditioning |
| bev_world_6f_waymo.pth | Waymo World Model |
Use the corresponding configuration from the UniAV-World code repository. World Model checkpoints include the tokenizer parameters. Training and evaluation require separately prepared dataset files and tokenizer latents.
Verify downloads
cd ckpts
sha256sum -c SHA256SUMS
nuScenes infos
Prepared train/validation annotation infos are available under nus_infos/.
They contain 28,130 training samples and 6,019 validation samples, respectively.
Download them into the code repository's data/ directory:
hf download JimmyLiaoo/LO-World --include "nus_infos/*.pkl" --local-dir data
The resulting paths are data/nus_infos/nuscenes_infos_train.pkl and
data/nus_infos/nuscenes_infos_val.pkl. Original nuScenes sensor data and
Occ3D occupancy labels must be downloaded separately.
BEVLayout conditioning data
The complete 2 Hz train/validation BEVLayout arrays used by the Layout-conditioned models are available under data/bev_layout/. The package contains 34,149 binary uint8 arrays of shape (18, 200, 200): 28,130 train and 6,019 validation samples. It is approximately 22.9 GiB uncompressed and 77 MiB as split Zstandard archives.
Download the package into the LO-World code repository and extract the arrays to data/bev_layout/:
hf download JimmyLiaoo/LO-World --include "data/bev_layout/**" --local-dir .
mkdir -p data/bev_layout
tar --zstd -xf data/bev_layout/2hz/train.tar.zst -C data/bev_layout
tar --zstd -xf data/bev_layout/2hz/val.tar.zst -C data/bev_layout
(cd data/bev_layout && sha256sum -c SHA256SUMS)
These are 2 Hz keyframe layouts, not dense 12 Hz frames. The arrays are derived from nuScenes and are for non-commercial research use subject to the nuScenes terms. See the package card for format, split manifests, checksums, source terms, and citation.
Selected 12 Hz validation conditions
The repository also includes BEVLayout conditions for 150 selected nuScenes validation scenes, with one 81-frame (12 Hz) clip per scene. Each NPZ stores 80 future layouts; the initial keyframe layout is in the 2 Hz validation archive above. Download this folder to reuse the prepared conditions without regenerating them:
hf download JimmyLiaoo/LO-World --include "data/bev_layout/12hz_val150_81f/**" --local-dir .
(cd data/bev_layout/12hz_val150_81f && sha256sum -c SHA256SUMS)
The manifest paths are repository-relative. The train700 and val150 packs together provide 850 selected scenes × 81 frames. See the train package and validation package.
Download the selected training conditions with:
hf download JimmyLiaoo/LO-World --include "data/bev_layout/12hz_train700_81f/**" --local-dir .
(cd data/bev_layout/12hz_train700_81f && sha256sum -c SHA256SUMS)