We observe that Adam’s performance in training transformers degrades differently under different types of random rotations of the objective function, highlighting the need for new, basis-dependent theory to fully understand Adam’s success.

A neural operator framework that maps biologically interpretable embeddings of neuron models to realistic neuronal responses, thereby enabling the fast generation of ensembles of neuron models that capture experimental variability.

We introduce i-CIR—an instance‐level composed image retrieval benchmark with rigorously curated hard negatives—and BASIC, a training‐free VLM‐based method that centers and projects image embeddings.