Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
0 results for “geometry-aware”
Geometry-aware Incremental Neural Operator for Long-Horizon PDE prediction
Researchers introduced GeoIncNO, a new neural operator architecture designed to improve stability and accuracy in long-horizon autoregressive prediction of partial differential equations by structuring latent increments with geometric awareness and decoupling mean and fluctuation reconstruction.
Aug 13, 2026
Beyond Decision Boundaries: Relational Geometry Attacks on Contrastive Embedding Manifolds
Researchers introduced a new adversarial attack framework that corrupts the relational geometry of contrastive embedding manifolds—targeting similarity structure rather than classification decisions—and demonstrated severe performance degradation on verification systems like Markmatch.
Aug 12, 2026
Geometry-Aware R-Structured Kolmogorov-Arnold Networks
Researchers introduced GRS-KAN, a new neural architecture that embeds differentiable R-functions into Kolmogorov-Arnold Networks to explicitly encode geometric constraints and discontinuities, improving accuracy and interpretability on benchmark regression tasks with structured boundaries.
Published Jul 3, 2026 · Analyzed Jul 6, 2026