3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Adversarial patches can disrupt Vision-Language-Action (VLA) models by manipulating visual observations, leading to failures in robot control. However, it remains poorly understood which internal mechanisms underlie these failures and how targeted interventions can mitigate them. In this work, we mechanistically analyz...
The microlocal neural operator (MiNO) learns that object, a phase and amplitude in phase space, and recovers the solution by an oscillatory integral, whereas a physics-informed neural network with neural-tangent-kernel loss balancing stays near its initial error.
A backward-transport view for Z-loss is developed that separates the source's scalar amplitude and softmax shape from the transport factors, and shows that nearly identical forward Z-loss values can coexist with distinct logit-space Z-loss gradients and, after architectural and optimizer transport, distinct parameter u...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
