Every idea extracted from recent arXiv mathematics papers — verified and unverified. Click an idea to open its full card; badges show the empirical verdict.
Replace dense attention over structured object tokens with attention over role-filler tensor-product representations. A learned query specifies both a role and a filler, retrieves objects matching that binding, extracts a target role, and rebinds the extracted filler into an output object.
Replace the usual sum of pairwise modality similarities with a higher-order score based on the coordinatewise Hadamard product of all normalized modality embeddings. For modalities indexed by i=1,...,m, score a tuple using s(x_1,...,x_m)=\omega^\top(\bar g_1(x_1)\odot\cdots\odot\bar g_m(x_m)), where \omega is learned and \odot is coordinatewise multiplication. This adds explicit m-way interactions without concatenating raw features or introducing a joint encoder.
Augment a neural latent or sequence model with a Gaussian behavior head that predicts an entire future trajectory jointly from the observed prefix and planned inputs. Instead of recursively applying only a point predictor, condition the learned joint trajectory covariance on the available prefix, producing a corrected future mean and uncertainty that incorporates temporal correlations.
Freeze a randomly initialized single-layer transformer and use a constructed soft prompt to make its attention weights equal Gaussian-kernel weights over support examples. The resulting model performs Nadaraya-Watson regression in one forward pass, so task adaptation stores prompt tokens rather than modifying network weights. Prompt length becomes the number of kernel centers, while hidden dimension and prompt norm determine whether the required logits can be represented accurately.
Use predicted covariance reduction as a differentiable gate for selecting tokens, views, sensors, or retrieved demonstrations. The gate favors inputs with high expected information gain while accounting for acquisition cost, turning attention and data collection into active observability optimization.
Replace a portion of quadratic key-value attention or an external episodic table with a per-sample matrix fast memory updated by rank-one delta corrections. The memory directly learns a linear key-to-value map and can be carried across sequence segments, providing cheap online adaptation with constant state size per head.
Construct a robust covariance estimate of layer activations by replacing each feature with its empirical Gaussian normal score before eigendecomposition, then applying coordinate-wise nonlinear eigenvalue shrinkage rather than multiplying all eigenvalues by one scalar. Use the cleaned covariance to whiten activations or precondition updates to the associated linear layer. This targets unstable directions caused by small batches, heavy-tailed activations, and rare outliers while retaining…
Add a differentiable orientation-pooling layer after steerable filters or an orientation-bin expansion. It aggregates unoriented line evidence using doubled-angle vectors, so a feature at angle θ is identical to one at θ+π, while symmetric orientations cancel naturally instead of producing an arbitrary mean angle. Feed the network both the Cartesian order parameter and its magnitude-based confidence.
Add a recurrent associative matrix to each selected transformer layer so recent key-value relationships can be retrieved without retaining every past token or performing gradient updates. The matrix uses input-dependent retention and write gates, but retrieval is always performed from the pre-write state, preventing the current target from leaking into its own prediction. Frobenius-norm clipping makes the recurrent memory bounded and provides a direct stability control.
Replace fixed LoRA factors with a rank-adaptive moving subspace whose columns are augmented using derivative information from several Runge–Kutta stages. The optimizer integrates a matrix-valued gradient-flow approximation inside this enlarged left/right basis, allowing high-order motion of the adapter subspace while retaining a low-rank parameterization.
Replace ordinary absolute positional embeddings with coordinates on a learned flat torus and use dual-lattice Fourier characters as positional features. Control the covariance of the coordinate fundamental domain so that the paper's inequality guarantees a lower bound on the smallest nonzero positional frequency, preventing the learned periodic coordinate system from developing arbitrarily weak or nearly constant modes.
Build a low-rank trilinear attention module in which query, key, and value factors are constrained to the unit sphere and refined through a few proximal alternating sweeps. The proximal terms suppress factor oscillation and make each sweep improve a well-defined tensor interaction objective, offering a stable alternative to unconstrained tensor-power iterations.
Compute separate doubled-angle orientation order parameters for left and right image regions, then expose their sum and difference as symmetric and antisymmetric global features. This gives a network a low-dimensional inductive bias for global vertical structure versus left-right imbalance, while retaining magnitude channels that indicate when either readout is undefined because orientations cancel.
Wrap a nominal gradient-based optimizer with a diagonal sign matrix that flips updates independently for parameter blocks, while a scheduler tests candidate sign configurations using short-horizon decrease of a Lyapunov-like training energy. The wrapper never changes the magnitude of the nominal update, and when the effective sign pattern is constant, it should recover the behavior of the correctly oriented nominal optimizer after a finite search period.
Replace an unconstrained feature vector of size n+1 by the coefficients of a homogeneous degree-n binary polynomial and make the layer transform through the irreducible symmetric-power representation of GL_2(R). For n=4 this creates a five-channel equivariant feature block whose transformation law is exact rather than learned through augmentation.
Build a constrained autoregressive model whose initial logits are generated from a translation-invariant MPS associated with a local zero-mode construction. The MPS supplies a structured valid distribution before a Transformer residual is added, so the model starts on the constraint manifold instead of learning validity through a penalty.
Augment a graph neural network or graph transformer with counts of cyclic walks whose successive steps are required to be graph edges or graph non-edges according to a binary pattern. These features encode induced-subgraph structure that ordinary adjacency powers miss, and can be concatenated to the graph-level token or used as an auxiliary prediction target.
Replace an ordinary token aggregation step with a p-replica cyclic-equivariant block. Features are copied into p replicas, processed by shared operators, coupled through a cap-like bilinear interaction, and projected onto cyclic invariants. An auxiliary commutation loss enforces that applying the operator before or after the p-fold lift gives similar outputs.