Architecture ideas

Research ideas extracted from mathematics papers, categorized as Architecture.

Unverified 2026

Algebraic-Invariant Residual Layer

Represent a rational-like feature transformation with an auxiliary state y constrained by polynomial equations G(x,y)=0, and update x and y jointly along the tangent space of that constraint manifold. This creates residual blocks in which nonlinear feature identities remain consistent over many layers or time steps, reducing auxiliary-variable drift and potentially stabilizing rational activations and implicit recurrent dynamics.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Algebraic Invariant Quadratization Schemes for Cahn--Hilliard Equations arXiv:2607.11569
Unverified 2026

Residual-Update Halting

Replace activation-magnitude-based adaptive computation halting with a criterion based on the actual recurrent update and a local stability margin. The loop halts when the state change is small relative to state scale for several consecutive steps, avoiding pathological decisions when LayerNorm-driven dynamics cause the activation norm to collapse.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: LayerNorm as Implicit Gain Control in Looped Transformers arXiv:2607.10681
Unverified 2026

Projected Play-State Memory

Turn a recurrent or state-space memory into a constrained hereditary state: the latent state remains in a learned convex domain, and only input motion that reaches the boundary changes the plastic component. This creates a nonexpansive, rate-independent memory that should suppress unstable state growth and make the representation depend on meaningful cumulative changes rather than arbitrary update frequency.

Useful6/10
Difficulty4/10
Novelty5/10
Paper: Optimal history encoding for elastic-plastic hereditary laws: Sharp input and constitutive approximation arXiv:2607.09974
Unverified 2026

Swarmalator Token Organizer

Augment each token or graph node with a periodic latent position x_i and phase θ_i, then evolve these variables before attention or message passing. Tokens with similar phase attract in x, while tokens with similar position synchronize in θ, producing self-organized groups without an externally specified clustering objective. The coupling strengths J and K provide interpretable controls for aggregation and synchronization, and their sweep should expose the paper's four collective regimes and…

Useful6/10
Difficulty5/10
Novelty8/10
Paper: A solvable normal form for coupled swarmalators arXiv:2607.09810
Unverified 2026

Symplectic Recurrent Block

Use a symplectic Hamiltonian update as a recurrent or state-space neural block, preserving a learned modified energy across many layers or time steps. This targets residual and recurrent architectures where ordinary Euler updates accumulate drift during long rollouts.

Useful6/10
Difficulty5/10
Novelty5/10
Paper: Backward error analysis for matrix discretizations of 2-D Euler equations arXiv:2607.09549
Unverified 2026

Certainty-Equivalent Auxiliary Critic

For risk-sensitive or recursive objectives, add a separate network that predicts the conditional certainty equivalent of the next-state continuation value, rather than forcing the value network to approximate a nested nonlinear expectation directly. Train the value, policy, and certainty-equivalent heads with Bellman and first-order residuals jointly.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: Deep Learning for Dynamic Programming with Recursive Utility Using First-order Conditions arXiv:2607.09461
Unverified 2026

Thermodynamic Two-State Expert Gate

Add a slow latent two-state gate to a recurrent, state-space, or world-model network so that separate experts represent two qualitatively different dynamical regimes. Train the gate using the paper's two-state population and fluctuation mechanism rather than allowing an unconstrained softmax to average incompatible regimes. The model should allocate extra capacity near the gate's susceptibility peak, where regime uncertainty and forecast variance are predicted to be largest.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Structural Origin of Water Heat Capacity Anomaly from Classical and Quantum Simulations arXiv:2607.08957
Unverified 2026

Cross-Ratio Reversible Lattice Layer

Represent a hidden state as complex-valued points on a two-dimensional lattice and replace unconstrained local updates by the exact harmonic-quadrilateral completion rule from discrete conformal geometry. Given three corners of a plaquette, compute the fourth corner by a Mobius-rational formula enforcing cross-ratio minus one, then use a learned readout or forcing term for task-specific predictions. The layer supplies a hard geometric inductive bias and a directly measurable local constraint…

Useful6/10
Difficulty6/10
Novelty8/10
Paper: Integrability of Cauchy problems for discrete conformal maps and circle patterns arXiv:2607.08901
Unverified 2026

Innovation-Compensated Latent Policy

In a partially observed reinforcement-learning or model-based control agent, expose the state-estimator innovation to the action head through a dedicated residual feedback branch. The policy produces a nominal action from the estimated latent state, while a learned innovation-compensation branch corrects actions when observations disagree with predicted latent dynamics. This explicitly separates nominal policy behavior from estimation-induced corrections and should help during fast transients…

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Revisiting Certainty Equivalence: The Structural Coupling Between Estimation and Control in Underactuated Nonlinear Systems arXiv:2607.07276
Unverified 2026

Age-conditioned semi-Markov router

Augment a neural router with the age of its current expert or latent regime and use an age-dependent hazard to determine when switching is likely. Unlike ordinary token-wise softmax routing, the router can learn non-geometric residence times, suppressing unstable expert oscillations while still allowing rapid transitions when the current regime becomes inappropriate.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Semi-Markovian switching in a fluctuating harmonic trap: An age-structured formulation arXiv:2607.05173
Unverified 2026

Bilinear Input-Conditioned Koopman Cell

Replace an unconstrained input-conditioned recurrent transition with a bilinear latent update, so controls modulate a fixed linear latent dynamics matrix through low-rank state-input interactions. The resulting cell preserves the computational simplicity of linear propagation while representing multiplicative effects of actions that an additive control term cannot capture efficiently.

Useful6/10
Difficulty5/10
Novelty5/10
Paper: Koopman operator theory: fundamentals, control, and applications arXiv:2607.01819
Unverified 2026

Hankel Residual Observer

Attach a model-free residual-dynamics observer to a neural multi-step forecaster. Instead of asking the network to relearn persistent periodic or autoregressive disturbances, maintain a Hankel dictionary of recent forecast errors and use ridge reconstruction to predict the next residual sequence online. Add the predicted residual to the network forecast with a confidence-dependent correction gain.

Useful6/10
Difficulty4/10
Novelty7/10
Paper: Model-Free Disturbance Observer with Online Modification: Listening to MFDOOM arXiv:2607.07082
Unverified 2026

Reversible Mealy Token Mixer

Replace a recurrent token-mixing operation with a finite-state carrier scan over binary or quantized token features. The local transition table is constrained to conserve a scalar token weight and to be bijective, making the mixer reversible, constant-memory, and less prone to activation drift than a generic recurrent layer.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Invariant Measures for Soliton Systems Generated by Mealy Automata arXiv:2607.06942
Unverified 2026

Diffeomorphic gauge-fixing layer

Insert a differentiable spatial canonicalization module before a neural dynamics model. It estimates a smooth invertible coordinate transformation that places each input field in a common gauge relative to a reference template, predicts the next state in that gauge, and maps predictions back to the original coordinates. The module should reduce the need for the dynamics network to relearn identical laws under many smooth spatial reparameterizations.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: The Right Space for Dynamics: Numerics with Diffeomorphism Equivariance arXiv:2607.06536
Unverified 2026

Periodic CMV Unitary Recurrent Layer

Replace a dense recurrent transition matrix with a periodic CMV-style product of alternating local 2x2 unitary cores. The transition is exactly norm-preserving, has O(n) trainable parameters under periodic tying, and can be applied through local factor operations rather than stored as an n-by-n matrix. Use turnover refactorization when changing the ordering or boundary connection of cores, enabling a compact cyclic unitary state-space layer.

Useful6/10
Difficulty5/10
Novelty5/10
Paper: Fast computation of eigenvalues of periodic CMV matrices arXiv:2607.06400
Unverified 2026

Pole-Certified SSM Initialization

Extract a small set of stable exponential modes from an observed neural sequence and use them to initialize a diagonal or block-diagonal state-space model. Hankel-pencil eigenvalues propose the modes, while persistence across shifts and contour margins reject modes caused by noise or a short-lived background.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Determinant Characteristics and Argument-Principle Certification for Visible Poles in Meromorphic Continuation arXiv:2607.04568
✓✓ Beats tuned baseline 2026

Cyclic Lie-Bracket Residual Block

Replace one deterministic residual update with a short cyclic composition of learned vector fields evaluated for randomized, short run times. Because finite compositions of noncommuting flows generate directional-derivative and Lie-bracket terms, changing the cycle order gives the network an explicit, low-cost way to learn drift directions that are unavailable from the individual vector fields alone.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Diffusion limits of cyclic finite-velocity random motions along vector fields arXiv:2608.22514
Failed on benchmark 2026

Laplace-Heterogeneous MoE Routing

Replace the usual hand-designed expert-load penalty with a heterogeneous survival penalty derived from a susceptibility distribution. Each expert receives an availability factor q_e=G(A_e), where A_e is its cumulative recent routing pressure and G_e is a learned or fixed mixture of exponentials; highly used experts are suppressed smoothly, while heterogeneous experts can have different resistance to pressure. The mixture produces adaptive curvature and long-tailed penalties that may reduce…

Useful6/10
Difficulty4/10
Novelty6/10
Paper: From Individual-Based Stochastic Epidemics to Heterogeneous SIR Equations arXiv:2608.22122
Failed on benchmark 2025

Log-Scale Self-Similar Activation

Replace a conventional scalar activation by a geometrically indexed family of affine pieces whose slope changes with the logarithmic magnitude of the input. The same two endpoint parameters are reused across all scales, giving a compact, explicitly scale-aware activation that can represent different responses for exponentially separated activation magnitudes.

Useful6/10
Difficulty4/10
Novelty7/10
Paper: From two-dimensional continuous maps to one-dimensional discontinuous maps: a novel reduction explaining complex bifurcation structures in piecewise-linear families of maps arXiv:2512.02291
Unverified 2026

Heisenberg Bracket Positional Encoding

Replace or augment standard sinusoidal or RoPE position features with bracket-quadratic phases $e(-\theta n\lfloor\beta n\rfloor)$ generated by a Heisenberg nilmanifold orbit. Multiple irrational coefficients and output frequencies produce a cheap deterministic encoding whose empirical cross-position correlations should exhibit cancellation instead of the periodic aliasing of rational or finite-frequency encodings.

Useful5/10
Difficulty3/10
Novelty7/10
Paper: Sets whose differences avoid a bracket quadratic arXiv:2608.30078
Unverified 2026

Braid-word reversible mixer

Replace a dense token- or channel-mixing matrix with a product of local braid generators acting on adjacent coordinates. Each generator is an exactly invertible 2-by-2 transformation, while the braid and far-commutativity identities give multiple equivalent factorizations of the same global operator. This creates a sparse, reversible mixer with O(kn) cost for a braid word of length k, rather than O(n^2) cost for a dense matrix.

Useful5/10
Difficulty4/10
Novelty7/10
Paper: Fox $p$-Colorings as Fixed Points of Braid Representations arXiv:2608.29046
Unverified 2026

Lattice Monodromy Residual Block

Insert a fixed reversible lattice shear into a residual network so successive blocks follow a structured monodromy orbit rather than using unrelated learned transformations. Apply the transformation to a small learned subspace of hidden channels while leaving the remaining channels unchanged. This creates deterministic phase-dependent feature mixing with no additional trainable parameters.

Useful5/10
Difficulty5/10
Novelty8/10
Paper: $G_2$-Manifolds from 4d $\mathcal{N}=1$ Quivers arXiv:2608.21238
Unverified 2026

Holonomy-composed latent transformations

Replace unconstrained transformation composition in a geometric or sequence encoder with time-dependent Lie-algebra controls whose flows compose according to the paper's flow-product rule. Add a holonomy consistency loss so different control trajectories that induce the same endpoint automorphism produce the same latent transformation, reducing sensitivity to arbitrary path parameterization.

Useful5/10
Difficulty6/10
Novelty7/10
Paper: On the holonomy of Lie algebroids arXiv:2608.19399
Unverified 2026

Companion Observer Memory for Neural Policies

Replace an unrestricted GRU or attention-based history encoder with a fixed companion-form shift register driven by the current action and observation, followed by a learned nonlinear policy. The register stores a structured finite history, while a learned matrix or MLP readout maps that history to a control-relevant latent state. This should provide a cheaper and more interpretable memory mechanism for partially observed environments, especially when the relevant dynamics are approximately…

Useful5/10
Difficulty4/10
Novelty6/10
Paper: Data-Driven Output Feedback based Analysis and Control for Unknown Discrete-Time Linear System arXiv:2608.18452