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 learned Riesz-transform branch that extracts normalized spatial gradients after diffusion by a positive parabolic operator. The diffusion branch carries smooth semantic content, while the Riesz branch represents boundaries, motion changes, and graph discontinuities. Resolvent smoothing makes the derivative branch less sensitive to feature noise than directly applying a finite difference.
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.
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.
Parameterize a relative-position or lag-decay function as a finite positive mixture of exponentials instead of learning arbitrary attention bias values. The resulting kernel is completely monotone on positive distances, so it is nonnegative, decreasing, and has alternating derivative signs; the mixture provides several learned memory scales without allowing oscillatory or unstable long-range biases.
Replace dense token-to-token attention by a learned binary relation generated from a small number of hierarchical predicates, while rejecting masks that contain a fixed K_{t,t} biclique. The paper's incidence bound predicts near-linear active edges for these structured relations, giving sparse attention with a measurable worst-case complexity target rather than relying only on average sparsity.
Construct a directional attention head whose admissible slopes are leaves of an M-adic interval tree with a prescribed finite splitting number. Instead of evaluating all K directions independently at every spatial location, route each query through only the branch decisions of the tree and share feature projections among directions that remain in the same multiscale angular interval.
Construct a sparse attention support by solving multiple small perturbed assignment problems between query and key embeddings and taking the union of the selected optimal matchings. Use the resulting spanning tree as the only set of cross-token edges, with edge biases determined by empirical assignment frequency.