Skip to content

Author

Pietro Lio'

We have 5 of 84 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

LocaLeJEPA: Maximum Entropy Representations under Geometric Priors

Joint-Embedding Predictive Architectures (JEPA) offer an appealing approach to self-supervised learning, but are typically prone to representation collapse. LeJEPA resolves this by introducing a theoretically grounded distribution-matching objective that drives the embedding towards an isotropic Gaussian. However, this...

Kartik Tandon, Alessio Borgi, Pavel Snopov et al. · 0 citations
Open access Oct 2026

AGraphHF: Adversarial graph-based multimodal learning for heart failure risk prediction.

Heart failure (HF) is a major cause of morbidity, mortality, and healthcare utilization worldwide, yet early risk stratification remains challenging because prognostic information is distributed across heterogeneous clinical narratives and subtle electrophysiological abnormalities. We propose AGraphHF, a multimodal fra...

Mamo Tadiyos Hailemichael, M. Hasanuzzaman, Haibo Wang et al. · 0 citations
#machine learning Preprint Oct 2026

BitSparse: Compact Activation Storage for ReLU Feed-Forward Networks

Reducing memory use in large language model (LLM) training is an ongoing challenge. Activation checkpointing saves memory by recomputation, while lossy compression changes the stored activations. The reemergence of sparse $\relu$ and $\relu^2$ activations creates a third opportunity: losslessly compressing the activati...

Max Zhu, Bo-Han Sun, P. Lio' et al. · 0 citations
#artificial intelligence Open access Sep 2026

AutoHGNN: Robust and efficient neural architecture search for hypergraph neural networks

This paper proposes AutoHGNN, a neural architecture search framework tailored for hypergraph neural networks, and introduces a Hyper-Interaction Module (HIM) into the search space to address the mismatch between conventional graph neural network designs and hypergraph data.

Sirui Li, Pietro Lio', Xin-Sheng Li et al. · 0 citations
Open access Aug 2026

De novo design of RNA pseudoknots with deep learning.

It is shown that intricate RNA structures can be generated with current deep learning tools through accurate de novo design of pseudoknot secondary structures, suggesting that some difficult RNA design tasks may be tractable without first solving RNA 3D structure prediction.

J. Townley, W. Kladwang, David Baker et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.