AcrossVAM1.0：文本辅助机器人视频预测的粒子世界建模
Original title: AcrossVAM1.0: Particle World Modeling for Text-Assisted Robot Video Prediction
ResearchAI 70
Source: arXiv cs.ROPublish time unverified
arXiv:2608.28491v1 Announce Type: cross Abstract: Predicting robot videos requires both precise motion reasoning and preservation of high-frequency appearance, yet monolithic pixel models entangle these objectives and often conceal their progress behind a strong last-frame baseline. We present AcrossVAM1.0, a lightweight, text-assisted video action model that factorizes future prediction into object-centric motion and dense appearance.