★ 30 +2 ⑂ 5 Python MIT 新项目 70

wadeKeith/SimpleMemVLA

Native-video memory for vision-language-action models, using timestamped visual history and exact streaming inference for long-horizon robot manipulation.

GitHub 主页 README

创建于 2026-08-29 · 最近推送 2026-09-09 · 首次出现在推荐 2026-09-10

embodied-ailong-horizon-roboticsmultimodal-learningnative-video-memoryrobot-learningrobot-manipulationstreaming-inferencevideo-understandingvision-language-actionvisual-memoryvla robotmanipulationVLAvision-language-actionembodied

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