Tag
This paper presents LingBot-VLA 2.0, which enhances VLA foundation models for robotics by improving generalization across tasks and embodiments, expanding action space to whole-body degrees of freedom, and incorporating predictive dynamics modeling for better temporal reasoning.
This paper identifies a threshold in decision capacity that determines whether self-play reinforcement learning agents collapse under asymmetric rule perturbations, showing that eliminating all positive-reach contingent decisions leads to rapid convergence to a deterministic exploitation attractor.