Download README.md from Efficient-Large-Model/Long-WAM-LIBERO-IDM: direct link, hf CLI and curl.
- Browser
- Download file 1.33 kB
-
https://huggingface.co/Efficient-Large-Model/Long-WAM-LIBERO-IDM/resolve/refs%2Fpr%2F1/README.md
- Command line
-
hf download hf://Efficient-Large-Model/Long-WAM-LIBERO-IDM@refs/pr/1/README.md
-
curl -L -o README.md https://huggingface.co/Efficient-Large-Model/Long-WAM-LIBERO-IDM/resolve/refs%2Fpr%2F1/README.md
library_name: pytorch
license: other
pipeline_tag: robotics
tags:
- long-wam
- libero
- idm
Long-WAM LIBERO-IDM
Long-WAM policy weights for LIBERO. IDM predicts actions after generating future-video latents.
For more details, refer to:
- Paper: Long-WAM: Scaling the Context of World-Action Models
- Project page: Long-WAM project
- Code: GitHub repository
Download
hf download Efficient-Large-Model/Long-WAM-LIBERO-IDM --local-dir ./weights/Long-WAM-LIBERO-IDM
Inference
Load model.pt with the matching Long-WAM runtime, using config.yaml and
the supplied dataset_stats.json for preprocessing and normalization.
P48 context uses 48 past control steps plus the current observation, encoded into four clean latent frames.
Generate two future-video latents using 4 steps (imagination sigma 0.9), then predict a 32-step action chunk using 10 action steps. Use the matched LIBERO execution cadence. Reset history at the start of each episode.
The matching inference runtime and base-model VAE/text assets are required separately. This release contains weights and inference settings only; optimizer states and training artifacts are not included.