We introduce TRoVe, an automated approach for discovering error-inducing static feature biases learned by temporal VLMs.

We improve training of spiking neural networks for energy-efficient robotic control by analyzing surrogate gradient slopes and introducing a privileged policy-guided method, achieving a 2.1× performance boost and strong real-world results.

A dataset containing neural activity and finger kinematics from 303 sessions of a monkey performing a 2-DOF finger movement task, recorded over a 1242 day (~3.5 year) timespan.