README.md

metadata

license: mit
library_name: pytorch
pipeline_tag: robotics
tags:
  - robotics
  - world-model
  - planning
  - pusht
  - ogbench
  - libero
  - robotwin
datasets:
  - CLTRAY/SAGE-data
arxiv: 2607.17973

SAGE

Official checkpoints for SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning.

Paper | Code | Datasets

SAGE combines latent subgoal generation and goal-conditioned action proposals with a frozen world model for planning.

Checkpoints

Environment	Subgoal generator	Action prior	Far-goal action prior
PushT	pusht_generator.pt	pusht_action_prior.pt	pusht_far_action_prior.pt
OGBench Cube	cube_generator.pt	cube_action_prior.pt	cube_far_action_prior.pt

Environment	World model directory
LIBERO Scene2	libero_scene2/world_model/
LIBERO Caddy	libero_caddy/world_model/
RoboTwin A2B	robotwin_a2b/world_model/

Each world model directory contains weights.pt and config.json.

Usage

Download the checkpoints with the Hugging Face Hub:

from huggingface_hub import snapshot_download

snapshot_download(repo_id="CLTRAY/SAGE", local_dir="checkpoints")

See the code repository for installation and evaluation commands, and native benchmark instructions for LIBERO and RoboTwin.

Citation

@article{cheng2026sage,
  title={SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning},
  author={Cheng, Letian and Zhang, Qi and Wang, Yisen},
  journal={arXiv preprint arXiv:2607.17973},
  year={2026}
}