★ 130 +7 ⑂ 3 Python MIT 新项目 75

rzc156/dreamforge

Turn world-model imagination into corrective training data for robot policies — a single-GPU, falsifiable pipeline (SmolVLA · LIBERO · CEM · paired simulator replays).

GitHub 主页 README

创建于 2026-10-12 · 最近推送 2026-10-12 · 首次出现在推荐 2026-10-13

embodied-aiimitation-learninglerobotliberopytorchresearchroboticsvision-language-actionvlaworld-model robotVLAvision-language-actionembodied

兴趣：vision-language-action (VLA) models and foundation models for robots