Feed-forward 3D Gaussian Splatting predicts a scene from a few images, but our predictor is less accurate than its own Gaussians optimized per scene on those images. This gap lies mostly in the shape…
Robot imitation learning uses demonstrations from operators of varying skill, but selecting training data remains challenging. Existing methods score demonstrations using smoothness, diversity, or…
We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision…