World action models (WAMs) aim to answer a coupled physical question: given a task instruction, what motion should the robot execute, and how will that motion change the surrounding world? Most existing WAMs build on pretrained video generators and represent world evolution through images or visual latents. Robotic int...
Rui-Xiang Wang, Yong-Yi Su, Wen-Lve Zhou et al.· 2 citations
Rita is proposed as a novel RL paradigm that performs consistently superior to the supervised finetuning approaches and vanilla RL-finetuned frameworks and adopts a difficulty-aware data filtering strategy that selects informative easy-to-medium samples for RL using rollout error rate and reward variance.
Peng-Zhan Sun, Shiu-hong Kao, Shi-Jie Li et al.· 1 citation
This paper proposes TaskAnchor, a lightweight adapter that grounds task state by injecting execution context into the VLA's native input space, and real-robot experiments further validate reliable multi-stage execution.
Heng-Yan Liu, Wen-Lve Zhou, Bo Yue et al.· arXiv.org· 0 citations
Reactive vision--language--action (VLA) models struggle with long-horizon manipulation when visually similar observations can correspond to different actions depending on the task stage or interaction history. We refer to this ambiguity as task-state aliasing and introduce TaskAnchor, a lightweight adapter that grounds...
Heng-Yan Liu, Wen-Lve Zhou, Bo Yue et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.