{"id":"2602.23721","title":"StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation","url":"https://codeofpaper.com/paper/2602.23721","arxiv_url":"https://arxiv.org/abs/2602.23721","published":"2026-02-27","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}