Flow-based Vision-Language-Action (VLA) policies generate action chunks by transporting samples from a task-agnostic isotropic Gaussian source. As this source is conditioned on neither recent execution nor predicted future evolution, (i) it discards the local continuity established by recently executed motion. (ii) Eve...
Predictive Vision-Language-Action (VLA) models aim to improve robotic manipulation via future observation or world dynamics forecasting. However, existing approaches often fail to realize this potential and underperform direct action prediction models. We argue that these limitations stem from modality misalignment bet...
UniMPA, a Unified Memory-Prediction-Action model that addresses transition ambiguity by modeling the intended future state evolution through a shared action-grounded transition interface, is proposed.
World Action Models (WAMs) extend Vision-Language-Action (VLA) models by incorporating future visual dynamics into action generation. However, existing WAMs often utilize imagined futures with limited adaptation to evolving execution progress, potentially introducing distracting or unreliable predictive cues. This limi...
Yi-Jie Zhu, Zi-Tong Yu, Wei Li et al.· 0 citations
FoMoVLA is proposed, a framework that augments VLA representations with explicit spatio-temporal supervision by jointly learning future feature foresight and sparse 2D point tracking, enhancing the continuous action policy.
Wei Li, Peijin Jia, Yuan Ma et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
