activity
20242026
collaborators

9 papers

cs.LG2026

MXNorm: Reusing MXFP block scales for efficient tensor normalisation

Callum McLean, Luke Y. Prince, Alexandre Payot +2

Matrix multiplication performance has long been the major bottleneck to scaling deep learning workloads, which has stimulated the design of new accelerators that use increasingly l…

cs.LG2026

Optimal Formats for Weight Quantisation

Douglas Orr, Luka Ribar, Carlo Luschi

Weight quantisation is an essential technique for enabling efficient training and deployment of modern deep learning models. However, the recipe book of quantisation formats is lar…

cs.IR2026

UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG

Dobrik Georgiev, Kheeran Naidu, Alberto Cattaneo +3

Large language models (LLMs) frequently generate confident yet factually incorrect content when used for language generation (a phenomenon often known as hallucination). Retrieval…

cs.LG2025

Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs

Alberto Cattaneo, Carlo Luschi, Daniel Justus

Retrieval of information from graph-structured knowledge bases represents a promising direction for improving the factuality of LLMs. While various solutions have been proposed, a…

cs.LG2025

Elucidating the Design Space of FP4 training

Robert Hu, Carlo Luschi, Paul Balanca

The increasing computational demands of foundation models have spurred research into low-precision training, with 4-bit floating-point (\texttt{FP4}) formats emerging as a frontier…

cs.LG2025

The Role of Graph Topology in the Performance of Biomedical Knowledge Graph Completion Models

Alberto Cattaneo, Stephen Bonner, Thomas Martynec +4

Knowledge Graph Completion has been increasingly adopted as a useful method for helping address several tasks in biomedical research, such as drug repurposing or drug-target identi…