Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Add a per-feature or per-token state that accumulates recent stimulation and decays when stimulation is absent, then use a nonlinear decreasing gain to suppress repeatedly activated features. This creates short-term adaptation without changing the core transformer or recurrent weights: familiar inputs are processed with reduced gain, while novel inputs recover their full response.
Attach each token or graph node a learned scalar charge q_i and add a fractional stable kernel K_ij = exp(-tau D |q_i-q_j|^alpha) to the interaction mechanism. Constrain 0 < alpha <= 2, the exact range in which the kernel is positive semidefinite for arbitrary finite real charge sets, and optionally make tau layer-dependent to obtain multiscale interactions. This provides a principled alternative to unconstrained learned distance biases and can be used either as an attention-logit bias or as a…
Replace flat expert logits with scores generated by Gaussian increments on a binary routing tree. A leaf receives the sum of increments on its root-to-leaf path, so sibling experts have correlated logits and the router can learn nested coarse-to-fine specialization; an inverse-temperature schedule controls the transition from exploratory diffuse routing to sparse routing.
Replace independent Gaussian attention noise or unconstrained token routing with a directed-polymer path distribution over positions and layers. The router aggregates exponentially many monotone paths through temporally correlated random edge scores, producing heavy-tailed but spatially coherent routing and preventing attention from collapsing onto a single token. The paper's t^{2/3} wandering and t^{1/3} free-energy fluctuations become measurable diagnostics and tunable targets rather than…
Regularize a neural attention or routing distribution according to how quickly it mixes toward a specified graph-dependent target, instead of penalizing only entropy or one-hop variation. The regularizer discourages pathological concentration on isolated graph regions while still allowing meaningful local structure, because concentration is judged after several graph-constrained Metropolis-Hastings steps.
Replace iid dropout or iid activation noise on spatial tokens with fluctuations generated by a conserved diffusing density. Each token receives a positive mass variable whose total mass is preserved, while Poissonian stochastic flux produces correlated perturbations that explore coherent local patterns rather than independently corrupting every feature. The density is autonomous and detached from autograd, so the regularizer adds little computational overhead.
Replace scalar entropy penalties on attention maps with a matrix-valued heat-flow regularizer over a circular or periodic token coordinate. Each position stores a positive semidefinite matrix describing coupled heads, experts, or channels; heat smoothing is constrained by the sharp modified log-Sobolev and Bogoliubov–Kubo–Mori contraction rather than an arbitrary smoothing coefficient. This should suppress high-frequency routing noise while preserving positive matrix structure and reducing…
Use the model's non-monotonicity result to make graph connectivity a learned resource rather than assuming that every extra edge helps. An edge router assigns transmission scores but also charges a source-side collision cost for exposing an infected node to many susceptible neighbors. The resulting router can prune edges that increase competition and reduce useful reachability.
Calibrate the maximum attention logit in each head against the log-correlated extreme-value law instead of applying fixed clipping or a fixed max-norm penalty. Penalize only maxima that exceed the predicted log N minus three-quarter log log N baseline by an unusually large order-one fluctuation, allowing ordinary sharp attention while suppressing rare pathological spikes.