5 citations · 6 across the 7 of their papers we have counts for
4 papers · 1 filter
BitSparse: Compact Activation Storage for ReLU Feed-Forward Networks
Max Zhu, Bohang Sun, Pietro Lio +1
Reducing memory use in large language model (LLM) training is an ongoing challenge. Activation checkpointing saves memory by recomputation, while lossy compression changes the stor…
LCT: Losslessly Compressed Tensors with GPU friendly execution for Training
Max Zhu, Bohang Sun, Pietro Lio +1
Lossless tensor compression could reduce memory usage during training, but training requires tensors to be repeatedly re-encoded. We introduce Losslessly Compressed Tensors (LCT),…
FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models
Max Zhu, Adrián Bazaga, Pietro Liò
Learning computational fluid dynamics (CFD) traditionally relies on computationally intensive simulations of the Navier-Stokes equations. Recently, large language models (LLMs) hav…
HyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node Classification on Text-Attributed Hypergraphs
Adrián Bazaga, Pietro Liò, Gos Micklem
Hypergraphs are characterized by complex topological structure, representing higher-order interactions among multiple entities through hyperedges. Lately, hypergraph-based deep lea…