Skip to content
Dario Loi
Search
Menu

Publications


2026

A Metacognitive Framework for Test-Time Adaptation: Taxonomy and Research Challenges

METACOG-26

Test-time adaptation loses accuracy when the model updates on images from classes it never saw in training, which entropy cannot detect. Treating adaptation as metacognition, we classify twenty methods and show that a gate built on the model's internal concepts keeps accuracy stable.

Dario Loi, Gabriele Onorato, Antonella Coviello, Shahriar Rifat, Nathaniel D. Bastian, Francesco Restuccia

Topological Deep Learning Challenge 2026: Bridging the Gap

TAG-DS 2026

The 2026 Topological Deep Learning Challenge put graph neural networks and higher-order topological neural networks side by side in TopoBench, on synthetic graphs whose structure is set by design. Which family does better depends on the task. Our implementation of the directed sheaf neural network took first place in the graph neural network track.

Guillermo Bernárdez, Lev Telyatnikov, Mathilde Papillon, Marco Montagna, Louisa Cornelis, Louis Van Langendonck, more authors, Dario Loi, more authors, Nina Miolane

Implicit Sheaf Operators for Effective and Efficient Cellular Sheaf Learning

Preprint

Implicit Sheaf Operators make sheaf neural networks fast. They apply sheaf diffusion and sheaf convolution locally at each node without building the sheaf Laplacian, which cuts time, memory, and energy. Built on them, Sheaf Convolutional Networks can be more accurate than Neural Sheaf Diffusion on node classification benchmarks.

Gabriele Onorato, Dario Loi, Cristian Apostol, Nathaniel D. Bastian, Francesco Restuccia

Implicit Inversion turns CLIP into a Decoder

ICLR 2026, Poster

A frozen CLIP, run backward through an implicit neural representation, generates images from text with no decoder and no fine-tuning. The same setup supports style transfer, image editing, and probing what CLIP encodes.

Antonio D'Orazio, Maria Rosaria Briglia, Donato Crisostomi, Dario Loi, Emanuele Rodolà, Iacopo Masi

Topological Deep Learning Challenge 2025: Expanding the Data Landscape

TAG-DS 2025

The 2025 Topological Deep Learning Challenge asked the community to extend TopoBench with new datasets, benchmark tasks, and data pipelines. This report describes the challenge and what it received.

Guillermo Bernárdez, Lev Telyatnikov, Mathilde Papillon, Marco Montagna, Raffael Theiler, Louisa Cornelis, more authors, Dario Loi, more authors, Nina Miolane

2025