An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers 事件

An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers arXiv:2606.04752v1 Announce Type: cross Abstract: Transformers consuming multi-channel scalar signals must embed $C$ simultaneous values into one $d_{\text{model}}$-dimensional vector per time step. We empirically audit eight input encoders -- spanning a shared-scalar baseline, per-channel linear projections, an orthogonality regulariser, a nonlinear MLP stem, block-partitioned concatenation, channel-independent and chan