Attention variants, state-space and recurrent cells, normalization and token-mixing schemes — each tested against the standard block it replaces.
Use attention-graph hitting times to identify tokens whose information has not mixed through the network, then route only those tokens through additional Transformer blocks. Tokens with fast reachability exit early, while slow or isolated tokens receive more computation.
Replace an eigendecomposition-based spectral controller in a small recurrent or state-space transition layer with explicit polynomial projectors. Each hidden state is split into invariant modes, and each mode receives a separately constrained recurrent multiplier, enabling direct suppression of unstable modes or selective retention of long-memory modes using only matrix-polynomial evaluations.
Replace a fixed top-k expert count with a stochastic, token-specific fanout generated by a supercritical binary branching process stopped at a geometric time. The resulting number of active experts has finite mean but a power-law tail with log-periodic modulation, allowing most tokens to use little compute while reserving larger computation for difficult or ambiguous tokens.