News_34

Four papers “TetraGT: Tetrahedral Geometry-Driven Explicit Token Interactions with Graph Transformer for Molecular Representation Learning”, “Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses”, “GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning”, and “Revisiting Matrix Sketching in Linear Bandits: Achieving Sublinear Regret via Dyadic Block Sketching” have been accepted by ICLR 2026.