Unverified
2026
Use a fixed learned energy or score network but search over inference protocols with different mobility, temperature, and duration. Select the shortest protocol that reaches a target accuracy without exceeding a prescribed entropy-production budget, exploiting the paper's observation that computational accuracy does not uniquely determine the thermodynamic path.
Useful6/10
Difficulty6/10
Novelty8/10
Unverified
2026
Use the change in the policy-induced reachable set as a trust-region constraint, rather than limiting only parameter distance or KL divergence. A policy update is accepted when its predicted finite-horizon zonotope remains sufficiently close to the previous reachable tube and does not cross the safety boundary, yielding a dynamics-aware step-size ceiling.
Useful6/10
Difficulty7/10
Novelty8/10
Unverified
2026
Treat a slowly varying block of neural-network parameters as a coarse-grained stochastic process and continuously estimate both its covariance spectrum and its linear response to small artificial perturbations. Use the fluctuation–response mismatch as a feedback signal to tune injected parameter noise or minibatch size; the thermal Einstein relation is imposed only when a calibrated equilibrium-like regime is desired, while antisymmetric response components are retained as admissible…
Useful6/10
Difficulty6/10
Novelty7/10
Unverified
2026
Replace an unconstrained recurrent hidden-state channel with a two-dimensional oscillator constrained to the supercritical Hopf normal form. A learned control parameter can place the channel below threshold for decaying dynamics or above threshold for sustained periodic dynamics, while the cubic term bounds the amplitude and prevents recurrent-state explosion.
Useful6/10
Difficulty5/10
Novelty6/10
Unverified
2026
Replace a static MoE load-balancing penalty with a two-stage capacity allocator. First compute each expert's technically feasible token capacity from latency, memory, and overflow constraints; then redistribute capacity using cumulative proportional fairness so experts that were repeatedly under-served receive more capacity later. Constrain the redistribution by an explicit efficiency budget, so fairness cannot silently cause an uncontrolled increase in routing loss or expert compute.
Useful6/10
Difficulty5/10
Novelty5/10
Unverified
2026
For a learned control-affine latent dynamics model, replace the ordinary reciprocal barrier 1/h₀(z) with B(z) = s(z)/h₀(z), where h₀ is the physical safety margin and s is positive but depends on a velocity-like quantity whose derivative is directly affected by the action. This preserves the singularity at h₀ = 0 while giving the policy or safety projection layer first-order action authority over the barrier derivative.
Useful6/10
Difficulty5/10
Novelty8/10
Unverified
2026
Replace a uniformly time-stepped neural ODE or state-space layer with a finite set of neural dynamical modes and an event scheduler. The hidden state follows the smooth flow of the current mode until a learned guard function crosses zero, at which point the solver evaluates the state at the event, switches mode, and continues with the new dynamics; this avoids numerical smearing of hard routing, thresholding, and switching behavior.
Useful6/10
Difficulty6/10
Novelty6/10
Unverified
2026
Use a learned dividing surface between two modes or basins of a neural energy model, and regulate Langevin or diffusion noise using the measured one-way crossing flux. The surface should be aligned with an estimated saddle direction and should reject immediate recrossings, so the controller responds to genuine mode transitions rather than local oscillations.
Useful6/10
Difficulty6/10
Novelty7/10
Unverified
2026
Add two scalar adaptive gains to a neural controller or learned dynamical model: one estimates the unknown norm of the ideal neural approximation weights, and the other estimates the combined approximation, friction, and disturbance envelope. Sigma modification prevents unbounded gain growth, while the robust residual correction uses only these scalar estimates, independent of the number of neural features.
Useful6/10
Difficulty5/10
Novelty6/10
Unverified
2026
Train a small controller to choose the next integration step size in a learned dynamical model using only deviations of conserved or slowly varying quantities. Unlike standard local adaptive solvers, optimize the complete rollout objective, allowing a later coarse step to compensate for an earlier discretization error. The controller can reduce the number of model evaluations while preserving long-horizon behavior.
Useful6/10
Difficulty6/10
Novelty7/10
Unverified
2026
Add a stable linear latent state-space block whose controllability Gramian is trained toward a chosen positive-definite target using squared Bures–Wasserstein distance. Direction-specific semidefinite constraints can suppress disturbance amplification in nuisance coordinates while preserving controllability in coordinates needed for prediction.
Useful6/10
Difficulty6/10
Novelty7/10
Unverified
2026
Replace the generic nonlinear drift in a two-dimensional continuous-time recurrent cell by a learnable piecewise-linear Lienard restoring force. Fold breakpoints and jump breakpoints become explicit architectural controls for creating multiple oscillatory attractors, allowing hidden states to encode phase, mode, or periodic memory. Weak input coupling can select or perturb attractors while preserving the autonomous cycle structure.
Useful6/10
Difficulty6/10
Novelty7/10
Unverified
2026
Replace an unconstrained recurrent transition with block-diagonal planar rotations whose angles are learned or conditioned on a slowly varying context variable. The resulting hidden-state norm and each two-dimensional block energy are exactly invariant in the ideal recurrence, preventing exploding or vanishing recurrent dynamics while retaining phase information over long horizons.
Useful6/10
Difficulty4/10
Novelty4/10
Unverified
2026
Construct a recurrent or state-space layer whose equilibrium Jacobian is placed near a nondegenerate Bogdanov–Takens point, then use a small unfolding parameter to move between damped, oscillatory, and slowly relaxing regimes. Unlike eigenvalue-only initialization near one, this controls both the double-zero center structure and the quadratic nonlinear coefficients that determine the local phase portrait.
Useful6/10
Difficulty6/10
Novelty8/10
Unverified
2026
Partition a long integration interval into M short segments and assign one neural trajectory approximator to each segment. Instead of asking a single network to satisfy the ODE and initial condition over the entire horizon, construct every segment so that its value at the left boundary is exactly the terminal value predicted by the previous segment. This removes interface discontinuities from the optimization problem and should improve long-horizon trajectory accuracy and gradient stability.
Useful6/10
Difficulty5/10
Novelty6/10
Unverified
2026
Constrain a low-dimensional neural state-space model so that its vector-field Hessian approximately satisfies the paper's Pascal-Hessian condition. Combine the resulting latent dynamics with an observer correction driven by the prediction residual, giving a model whose hidden-state estimation error can be assigned a desired linear decay rate.
Useful6/10
Difficulty7/10
Novelty8/10
Unverified
2026
Attach a finite mixture of zonotopes to each uncertain neural input or hidden state, and propagate every mixture component through affine layers and conservative nonlinear relaxations. When the number of components grows, merge components only with an enclosing zonotope and sum their probability masses, preserving a formal lower bound on the probability that the true activation lies in the represented set.
Useful6/10
Difficulty6/10
Novelty7/10
Unverified
2026
Replace unconstrained latent or neural-ODE dynamics with a strict-feedback cascade whose virtual controls are generated recursively by nonadaptive backstepping. Add a fixed internal-model oscillator when the desired output contains known-frequency periodic components, so the network tracks persistent targets without learning an unstable long-memory representation. The controller is designed to tolerate bounded neural-model mismatch and disturbances through an input-to-state stability margin.
Useful6/10
Difficulty7/10
Novelty7/10
Unverified
2026
Augment a neural-network update with an auxiliary, damped stochastic branch that acts like the paper's floating dissipative reservoir. A trainable mixing phase \(\phi\) combines the task-gradient branch and auxiliary branch; \(\phi\) is adapted to make the auxiliary response to a chosen control perturbation nearly zero while retaining a finite task-gradient response. The intended benefit is selective insensitivity to nuisance hyperparameters or perturbations, with a measurable response peak…
Useful6/10
Difficulty6/10
Novelty7/10
Unverified
2026
Replace unconstrained or entropy-regularized MoE routing with a minimally disruptive update that preserves a lower bound on the log-determinant of the experts' weighted output span. The router still tracks the desired mixture, but a projection prevents the active experts from becoming linearly redundant or collapsing onto a low-rank subset.
Useful6/10
Difficulty5/10
Novelty7/10
Unverified
2026
Treat a selected neural submodule as an open dynamical system embedded in the rest of the network. Regularize it to contain internal modes that are simultaneously reachable from many external features and observable through many external outputs, rather than behaving as a one-sided receiver, broadcaster, or disconnected read/write split.
Useful6/10
Difficulty6/10
Novelty7/10
Unverified
2026
Use adaptive performance specifications to prevent a neural controller or policy from demanding output changes that exceed bounded actuator amplitude or action-rate limits. The target error envelope tightens when the policy has control authority and relaxes when saturation or rate clipping persists, instead of allowing the controller to destabilize while chasing an infeasible target. This converts actuator clipping into an explicit slow state that can be used by reinforcement-learning policies…
Useful6/10
Difficulty4/10
Novelty7/10
Unverified
2026
Represent recurrent hidden states as compact phases and monitor spacetime vortices, defined by wrapped phase differences around elementary space-time plaquettes. Add a feedback controller that increases relaxation toward the homogeneous phase when vortex activity becomes supercritical, while allowing larger recurrent gain when the system is excessively quiescent. This creates a falsifiable operating regime: useful computation should occur near, but below, the defect-proliferation transition…
Useful6/10
Difficulty6/10
Novelty8/10
Unverified
2026
Augment a recurrent or diagonal state-space neural block with online interval estimates for persistent transition gains. At every step, intersect the current parameter interval with the set compatible with the latest transition and bounded residual, then use its midpoint for certainty-equivalent cancellation. The method learns passively and avoids the transient spikes caused by exploratory probing or endpoint selection.
Useful6/10
Difficulty6/10
Novelty8/10