🏢 Texas A&M University

SMAG, a novel single-loop stochastic algorithm, achieves state-of-the-art convergence for solving non-smooth non-convex optimization problems involving differences of max-structured weakly convex func…

This paper presents novel statistical methods to reliably watermark and segment LLMs-generated text, ensuring source traceability even after user modifications.

Mat2Seq revolutionizes crystal structure generation using language models by creating unique, invariant 1D sequences from 3D crystal structures, enabling accurate and efficient crystal discovery with …

Gradient Rewiring (GRE) improves editable GNN training by addressing gradient inconsistencies, preserving training node performance while correcting target node errors.

Equivariant Blurring Diffusion (EBD) generates 3D molecular conformers hierarchically, first creating coarse-grained fragments then refining atomic details, significantly outperforming existing method…

Researchers surpass the 1/e barrier in submodular maximization with novel combinatorial algorithms!

Communication-efficient algorithms for federated group distributionally robust optimization (FGDRO) are introduced, achieving lower communication complexity and superior performance on real-world task…

New method recovers low-rank matrices with informative missingness, offering robust, near-optimal performance.