3 papers
cs.LG2026
Expressivity Saturation: Reduced Affine Region Usage Under Increasing Task Complexity
Xuan Qi, Yi Wei, Fanqi Yu +1
Piecewise-affine neural networks (e.g., with ReLU or LeakyReLU activations) implement continuous piecewise-affine maps, and the number of affine regions provides a natural proxy fo…
cs.LG2026
Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks
Xuan Qi, Yi Wei, Fanqi Yu +3
Batch normalization (BN) is central to modern deep networks, but its effect on the realized function during training remains less understood than its optimization benefits. We stud…
cs.CV2026
Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustment
Fanqi Yu, Matteo Tiezzi, Tommaso Apicella +2
We introduce a lifelong imitation learning framework that enables continual policy refinement across sequential tasks under realistic memory and data constraints. Our approach depa…