Architecture ideas

Research ideas extracted from mathematics papers, categorized as Architecture.

Unverified 2026

Resolution-adaptive spectral front end

Replace a fixed Fourier or spectral resolution in a neural operator or sequence model with a data-adaptive spectral cutoff. Keep only modes whose estimated signal energy exceeds the noise-amplification and discretization floor implied by the available number of trajectories and samples per trajectory. This should reduce overfitting to high-frequency sensor noise and preserve accuracy when the same model is deployed at different sampling resolutions.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: The Cost of Discretization in Functional Linear Regression: Minimax Rates and Adaptation arXiv:2607.09350
Unverified 2026

Resolvent Fractional-Power Layer

Parameterize a learned feature-space operator as accretive but not necessarily symmetric, then apply its fractional power through a finite positive mixture of shifted resolvents. This provides a matrix-function layer that can represent directional and rotational interactions while avoiding unstable eigendecomposition of nonnormal matrices.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Functions and Means of Accretive Operators arXiv:2607.09152
Unverified 2026

Rank-Adaptive Tensor-Train MLP

Replace a large dense layer whose input and output dimensions factor into multiple modes by a TT-matrix whose parameters are stored as a chain of small cores. Periodically apply TT-SVD rounding to remove weak singular directions and keep the representation within a prescribed approximation error. This transfers the paper's central computational principle—perform tensor-product contractions directly in compressed form—to neural network layers.

Useful6/10
Difficulty5/10
Novelty4/10
Paper: A Tensor-Train Discontinuous Galerkin Method for the Vlasov-Maxwell System arXiv:2607.08936
Unverified 2026

Trace-Canonical Modular Blocks

Represent a modular neural block as a word over primitive operators and identify operators that commute because they act on disjoint tensor supports. Canonicalize every equivalent word into one representative, allowing architecture search, caching, and parameter sharing to operate on equivalence classes rather than redundant layer orderings.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: Partially-Commutative Polynomial Optimization arXiv:2607.08841
Unverified 2026

Wide-tree invariant alignment layer

Replace a purely pairwise embedding similarity used for set alignment with a sum of rooted-tree contraction scores. Each tree feature aggregates products of several coordinate-level interactions and can preserve correspondence information under an unknown orthogonal transformation, allowing matching from moderate correlation rather than nearly identical embeddings. Use the resulting score matrix for Hungarian matching, contrastive loss, or a differentiable Sinkhorn assignment.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: High-Dimensional Procrustes Matching via Tree Counts arXiv:2607.08538
Unverified 2026

Finite-group relative message passing

Use the quotient group's generator classes as a finite relation vocabulary and tie message functions by group displacement instead of by individual graph edges. This creates a compact, exactly consistent relation-aware GNN that can recognize repeated local structure and transfer parameters across graph instances sharing the same Cayley geometry.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Minimal Isometric Embeddings of Graphs into Cayley Graphs of Finite Abelian Groups arXiv:2607.07920
Unverified 2026

Neighborhood-separator attention

Construct a sparse token-interaction graph from attention affinities and recursively split it by removing the closed neighborhoods of a small set of separator tokens. Separator tokens retain global communication, while the resulting anti-adjacent components perform local attention independently, reducing quadratic attention and KV-cache costs. The induced Erdos-Pósa theorem supplies a structural diagnostic: graphs with few anti-adjacent long-cycle or theta packings should admit small…

Useful6/10
Difficulty7/10
Novelty8/10
Paper: Induced Erdős--Pósa property for long holes, long thetas, and beyond arXiv:2607.07697
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

Compressed threshold-overlap Gram layer

Represent each k-element object by a vector in dimension \(r=\binom{n-2(k-s)}{s}\), and use a PSD Gram matrix to encode the rule that pairs with intersection smaller than s have zero similarity while pairs with intersection at least s have nonzero similarity. Insert this representation into set encoders, graph neural networks, or overlap-aware attention instead of allocating one feature for every s-subset.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Minimum-rank parameters of complements of threshold Kneser graphs arXiv:2607.06480
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

Canonical orbit search for symmetric pruning masks

Enumerate structured pruning masks only up to exact permutations of exchangeable channels, hidden units, or experts. Replace exhaustive mask search with canonical augmentation: retain a subset only when it is lexicographically smallest among all masks obtained by the model's symmetry group, while recursively generating only canonical predecessors.

Useful6/10
Difficulty5/10
Novelty8/10
Paper: Symmetric lexicographic symmetric-subset reverse search for the enumeration of circuits, cocircuits, and triangulations up to symmetry arXiv:2607.05967
Unverified 2026

Gain-Rigid Sparse Attention

Construct a sparse attention or message-passing graph as a gain graph, where every directed edge carries a relative frame label and reverse edges carry the inverse label. Grow the graph using the paper's 2-extension operation: replace two old edges by a new vertex connected to their four endpoints, while preserving the relative gain products. The resulting mask is intended to preserve global information flow under controlled sparsity and to avoid isolated components and brittle bridges commonly…

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Rigidity on compact surfaces through hyperbolic symmetries arXiv:2607.05023
Unverified 2026

Critical-Tail Multiscale Mixer

Add a fixed or weakly parameterized residual mixer whose interaction between sequence positions at distance \(r\) is proportional to \(1/(r\log^2 r)\). Instead of truncating the kernel at a short radius, represent its heavy tail with dyadic distance bands and compute each band using prefix sums or block pooling, giving every token access to arbitrarily distant context at roughly \(O(L\log L)\) cost.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Long-range interactions and Anderson localisation for one-dimensional high-contrast resonator chain arXiv:2607.04971
Unverified 2026

Unassembled Adaptive Cell Neural Network

Represent every mesh interface degree of freedom by one feature copy per incident cell, and apply local neural blocks directly to these cell tensors. Enforce inter-cell consistency with valence-weighted averaging only after selected layers or hierarchy transitions, avoiding repeated construction of a global sparse graph or assembled feature vector. This is suited to adaptive quadtrees, octrees, and finite-element neural operators.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: Coalesced Matrix-Free Geometric Multigrid on Persistent Cell-Wise Storage arXiv:2607.03413
Unverified 2026

Kolmogorov-Lie Unitary Layer

Build an input-conditioned unitary transformation as an ordered product of exponentials of anti-Hermitian matrices, with each factor controlled by a univariate function of one input coordinate or one learned scalar projection. This replaces a dense multivariate matrix-valued controller with separable scalar nonlinearities while preserving exact unitarity at every forward pass.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Quantum Kolmogorov--Arnold representation theorem for continuous unitary-valued maps arXiv:2607.03187
Mechanism works 2026

Degree-Corrected Hierarchical Router

Replace a flat MoE or graph-pooling assignment with recursive partitions selected by interaction evidence after removing each item’s expected degree effect. Tokens, nodes, or examples that are frequently active for purely popularity-related reasons should not automatically form an expert or cluster. Recursion stops when a candidate split has nonpositive degree-corrected evidence, producing an adaptive hierarchy rather than a fixed number of equally sized groups.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Community structure of the pseudofractal web arXiv:2607.03010
Unverified 2026

Singularity-Enriched Neural Ansatz

Add an explicit local power-law singular basis to a neural field near mixed Dirichlet-Neumann junctions, allowing the neural network to learn only the smoother remainder. Use the predicted or fitted singular exponent to concentrate collocation points near the junction. This directly targets the regularity bottleneck identified by the paper, where increasing polynomial degree or network capacity cannot overcome a convergence cap under uniform resolution.

Useful6/10
Difficulty5/10
Novelty7/10
Paper: A Unified CutFEM Formulation for Finite-Strain Elasticity: Energy Minimisation and Corner Singularities arXiv:2607.02334
Unverified 2026

Expander OMP Sparse Inference

Use the expander decoder as a structured sparse-coding dictionary and replace dense OMP correlation steps with edge-wise gather-and-reduce operations. This is useful when codes must be inferred iteratively, including interpretable feature extraction, sparse retrieval, or an inference-time latent selector that cannot rely entirely on an amortized encoder.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability arXiv:2607.01799
Unverified 2026

Orthogonal-Rank Contextual Memory

Replace a discrete or one-hot recurrent state table with a low-dimensional vector memory whose event embeddings are orthogonal whenever the corresponding events are mutually exclusive in an input exclusivity graph. The module uses continuous state vectors and can therefore target dimension \(d=\xi(G)\), whereas a discrete state encoding is lower-bounded by \(N\geq\chi(G)\). This should be tested on graph-defined formal-language recognition tasks, where the graph is known and the claimed…

Useful6/10
Difficulty6/10
Novelty7/10
Paper: Quantum Memory Advantage from Contextuality arXiv:2607.00507
Unverified 2026

Independent-Simplex Hypergraph Router

Use the paper's edge-to-area incidence structure to choose a small set of geometrically independent simplices instead of processing every possible hyperedge. A greedy rank-increasing router retains a triangle only when its Jacobian adds a new direction, reducing higher-order message-passing cost while preserving diverse geometric information.

Useful6/10
Difficulty6/10
Novelty7/10
Paper: On volume vectors determined by hypergraphs in thin subsets of Euclidean space arXiv:2607.00153
Unverified 2026

Collision-Aware Subset Attention

Replace ordinary one-token-to-one-expert or one-token-to-one-attention routing with a local latent subset router: a pooled observation can be explained by a compatible subset of tokens. Pairwise compatibility scores assign probability to subsets, and each token receives the marginal probability that it belongs to the selected subset. This should help when tokens represent overlapping objects, occluded entities, or multiple features that should be processed jointly.

Useful6/10
Difficulty5/10
Novelty6/10
Paper: Gaussian Belief Propagation for Tracking With Unresolved Measurements arXiv:2606.31716
Unverified 2026

Fast-Class MoE Router

Replace a flat stochastic MoE router by a two-level continuous-time routing model: experts within a group communicate rapidly, while transitions between groups occur slowly. Use the effective class-level stationary distribution as a soft load-balancing prior, reducing routing oscillation while preserving expert specialization.

Useful6/10
Difficulty6/10
Novelty6/10
Paper: The Invariant Measure of Multiscale Markov Chains via Fast Arborescence Factorization arXiv:2606.31596
Mechanism works 2026

Modular collision-free sparse attention

Replace dense attention between grid-arranged tokens by a deterministic block-sparse pattern generated from modular permutations. In each block, connect row token i to column token p(i)=2i modulo B; because i, i-p(i), and i+p(i) are injective modulo B when gcd(B,6)=1, the pattern avoids repeated horizontal, vertical, and diagonal projections. Use shifted permutations across heads to increase receptive-field coverage while retaining structured sparsity.

Useful6/10
Difficulty4/10
Novelty6/10
Paper: Closing the gap and settling the problem of queens on an $n\times n$ board, each attacking at most one other arXiv:2608.27432
Unverified 2026

Minkowski-Additive Convex Latents

Store a convex object as a direction-indexed vertex tuple and implement composition of objects through componentwise Minkowski addition and nonnegative scaling. This creates a structured residual or compositional layer where convexification is nonexpansive, making perturbation amplification controllable and avoiding repeated generic geometric optimization.

Useful6/10
Difficulty4/10
Novelty8/10
Paper: Galerkin approximations to the space of convex bodies by polytopes in nondegenerate V-representation arXiv:2608.26615