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
DrGait is introduced, a training-free agentic framework that shifts the VLM's role from a direct visual reasoner to a clinical planner, and anchoring VLM's reasoning in verifiable geometric and temporal measurements, reduces hallucinations.
Xiang-Yu Yin, Shi-Qi Wang, Abrar Alamri 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.