3 papers
cs.CE2026
HypeR Adaptivity: Joint -Adaptive Meshing via Hypergraph Multi-Agent Deep Reinforcement Learning
Niccolò Grillo, James Rowbottom, Pietro Liò +2
Adaptive mesh refinement is central to the efficient solution of partial differential equations (PDEs) via the finite element method (FEM). Classical -adaptivity optimizes verte…
cs.CL2026
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
Victor Conchello Vendrell, Arnau Padres Masdemont, Niccolò Grillo +3
Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space without generating intermedia…
cs.LG2025
Beyond Interpolation: Extrapolative Reasoning with Reinforcement Learning and Graph Neural Networks
Niccolò Grillo, Andrea Toccaceli, Joël Mathys +3
Despite incredible progress, many neural architectures fail to properly generalize beyond their training distribution. As such, learning to reason in a correct and generalizable wa…