Skip to page content
SAVRN
Search Plan a project

Organization

WB-WAM

WB-WAM

WB-WAM: world-action modeling for whole-body humanoid loco-manipulation.

Models in Library2
Datasets in Library2
Models on Hugging Face2
Followers4

Compare the published evidence

This profile connects the 4 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Published tasks: Robotics.

Reported licenses: apache-2.0. Open a record to review its specific license and conditions.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Models

Model · Robotics

WB-WAM-HumanoidArena

WB-WAM

This repository contains seven HumanoidArena post-train checkpoints under humanoidarenanative50/: boxshelf, hammer, kickfootball, obstaclenavigation, opendoor, punchmarkers, and sitsofa. Each task directory has a checkpoint, its resolved training config.yaml, and datasetstats.json. Post-training uses official SONIC reference actions at their native 50 Hz rate, with separate normalization statistics for each task. Download the HumanoidArena checkpoints into a local directory: Training and evaluation instructions are in the WB-WAM repository. These results were obtained with Isaac Sim 5.1.0 on an NVIDIA RTX 5090 GPU, using three seeds and 20 episodes per seed for each task. Values are the…

Open weights apache-2.0

Model · Robotics

WB-WAM-Pretrain-Midtrain

WB-WAM

This repository contains the full pre-train checkpoint and the PICO mid-train checkpoint. The mid-train model was initialized directly from the pre-train model. Each checkpoint has its resolved training config.yaml and datasetstats.json. Training code and instructions are in the WB-WAM repository.

Open weights apache-2.0

Datasets

English · 中文 Real-robot data collected with SONIC for WB-WAM task post-training. LeRobot v3.0, 20 Hz, RGB 360 × 270. The release contains 1,011 episodes, 242,668 frames, 8 tasks, and 12 independent recordings (3.370 hours). Each /recordXXXX/ is an independent LeRobot dataset. Recordings of the same task remain separate: The Dataset Viewer plays the MP4 files. The corresponding Parquet state/action rows and metadata are available under each recording in Files and versions. The action contains absolute next-frame joint targets (+50 ms), not joint increments. Root[3] denotes roll, pitch, and body-frame z angular velocity, not XYZ position. The original train/validation labels are retained in…

Publicly accessible

Dataset

Pico

WB-WAM

English · 中文 Pico motion-transfer data for WB-WAM intermediate training. LeRobot v3.0, 20 Hz, RGB 360 × 270. The release contains 13,396 episodes, 1,579,028 frames, 73 tasks, and 302 independent recordings (21.931 hours). Each /recordXXXX/ is an independent LeRobot dataset. Recordings of the same task remain separate: The Dataset Viewer plays the MP4 files. The corresponding Parquet state/action rows and metadata are available under each recording in Files and versions. The action contains absolute next-frame joint targets (+50 ms), not joint increments. Root[3] denotes roll, pitch, and body-frame z angular velocity, not XYZ position. Pico hand data may include reconstructed or held values.…

Publicly accessible