Dario Loi

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

Fri, 06 Nov 2026 00:00:00 GMT

AAAI 2026 Fall Symposium on Artificial Metacognition (METACOG-26), Top 3 paper. Dario Loi, Gabriele Onorato, Antonella Coviello, Shahriar Rifat, Nathaniel D. Bastian, Francesco Restuccia.

In Test-Time Adaptation, when out-of-distribution samples interleave unpredictably with corrupted in-distribution samples, adaptation without corrective measures is prone to significant performance decrease. Existing protocols rely on unreliable cues (e.g., predictive entropy) which are unable to distinguish corrupted in-distribution data from semantically novel open-set samples. To address this issue, we formalize Test-Time Adaptation through a two-level metacognitive framework that decouples task execution from control, facilitating a unified taxonomy that categorizes existing Test-Time Adaptation protocols across three core axes, i.e., which knowledge is monitored, which part of the models are targeted for adaptation, and how adaptation occurs. We provide evidence that robust corrective measures in Test-Time Adaptation require monitoring grounded in structured internal representations to reliably estimate model competence. Lastly, we frame monitoring as a resource-allocation problem, examine neuromorphic substrates for bounded self-regulation, and outline key open challenges.

A Metacognitive Perspective on Anomaly Detection with Vision Foundation Models

Fri, 06 Nov 2026 00:00:00 GMT

AAAI 2026 Fall Symposium on Artificial Metacognition (METACOG-26). Matteo Galiazzo, Gabriele Onorato, Dario Loi, Nathaniel D. Bastian, Francesco Restuccia.

Anomaly Detection (AD) in images identifies defective regions by scoring against a model of normality learned from defect-free data. Current state of the art methods encode images via a frozen Vision Foundation Model (VFM) backbone and score them by their Nearest-Neighbor (NN) distance to a memory bank of normal samples. Recently, due to the parallel evolution of VFM encoders and scoring mechanism, the need to disentangle their individual contributions has emerged, in order to guarantee the deployment of the best performing model in specific industrial production environments. In our work, we analyze AD within a metacognitive perspective, we freeze the backbone and swap the scorer, replacing NN distance with a Mahalanobis score over a Gaussian distribution. By doing that, we can evaluate two different metacognitive functions of the scoring mechanisms: monitoring how far an observation is from the learned model of normality via a threshold-free metric, and deciding when the difference justifies an action according to a threshold. We show that these two metacognitive functions can dissociate. We further notice that replacing a NN memory bank with a simpler Mahalanobis model improves pixel-level monitoring (+8.00 AU-PRO$_{0.05}$ on MVTec AD 2) while degrading the segmentation performance after the thresholding step $(-13.46\ F_1)$. Lastly, we show that a threshold derived by Extreme Value Theory (EVT) recovers that loss without using anomalous data: the decision stops contradicting the monitoring signal, the $F_1$ difference between the two scorers decreases from 13.46 to 0.61 points on MVTec AD 2, with consistent gains on MVTec AD and VisA.

Topological Deep Learning Challenge 2026: Bridging the Gap

Tue, 03 Nov 2026 00:00:00 GMT

2nd Conference on Topology, Algebra, and Geometry in Data Science (TAG-DS 2026), First place, Track 1 (GNNs). Guillermo Bernárdez, Lev Telyatnikov, Mathilde Papillon, Marco Montagna, Louisa Cornelis, Louis Van Langendonck, Antonio Purificato, Bruno Neri, David Leko, Donatella Genovese, Eleonora Grassucci, Jan-Willem Van Looy, Johan Mathe, Lucia Testa, Luka Benić, Melanie Weber, Olga Zaghen, Pavlo Vasylenko, Raffael Theiler, Scott Mahan, Gaurav Khanal, Valentina Sánchez, Dario Loi, Gabriele Onorato, Prasanna Devadiga, Taejin Paik, Anier Velasco Sotomayor, Jonas Müller, Aarav Gupta, Riyan Patel, Grold Otieno Mboya, Pushparaj Devadiga, Adam Gohain, Dominik Filipiak, Michael Banf, Alireza Mohammadian, Amirreza Akbari, Gabriel Chaviano Díaz, Marcos Chávez Mesa, Ankit Grover, Rémi Bourgerie, Alessio Comparini, Ankit Kumar, Mohammad Yusuf, Devesh Kaushal, Francesco Orsi, Ghazal Mostofi, Kolya Lettl, Salwa Khattami, Gabriel Franco, Yelizaveta Falkouskaya, Jorge Luiz Franco, Kajal Singla, Fernando David Espinosa Iñiguez, Raj Patil, Eric Dolores-Cuenca, Luigi Petti, Chenguang Xu, Stefano Blando, Christine Zeh, Lennart Bastian, Kaden Zheng, Vihan Tiwari, Sud Athreya, Hisataka Kajita, Hugo Micheron, Rémi Devaux, Antoine Jardin, Tegan Emerson, Olga Fink, Nina Miolane.

This paper describes the 2026 edition of the Topological Deep Learning Challenge: Bridging the Gap, hosted at the second Topology, Algebra, and Geometry in Data Science (TAG-DS) Conference. Where previous editions grew the modelling and data ecosystem of Topological Deep Learning (TDL), this edition set out to place Graph Neural Networks (GNNs) and Topological Neural Networks (TNNs) side by side under a single evaluation pipeline. Participants implemented recent state-of-the-art architectures in TopoBench, with Track 1 covering GNNs and Track 2 covering TNNs. They evaluated these implementations on shared synthetic benchmarks generated with GraphUniverse, which independently controls homophily, average degree and degree-distribution heaviness. The challenge yielded 68 qualifying submissions from 34 teams, spanning the graph, simplicial, cellular, hypergraph and combinatorial domains. For the first time, submissions were also tracked on a public leaderboard, which we summarize and analyze here. Our analysis finds that the differences between the submitted tracks are strongly task-dependent: the mean accuracy gap is modest on community detection, while on triangle counting the Track 1 mean error is 1.85 times the Track 2 mean. Several structurally informed GNNs also outperform the Track 2 mean on triangle counting.

Polytope

Sun, 11 Oct 2026 00:00:00 GMT

A design system for academic sites, paper pages, and research demos: tokens, CSS components, Astro components, and plotting themes compiled from one token file. Open source, Apache 2.0.

Implicit Sheaf Operators for Effective and Efficient Cellular Sheaf Learning

Tue, 04 Aug 2026 00:00:00 GMT

Preprint, August 2026. Gabriele Onorato, Dario Loi, Cristian Apostol, Nathaniel D. Bastian, Francesco Restuccia.

While Sheaf Neural Networks (SNNs) enrich $n$-node $m$-edge diffusion of $f$-dimensional node features with $d$-dimensional node and edge stalks, they require computing a sparse $nd \times nd$ sheaf Laplacian, whose computation is prohibitive on edge devices. This paper addresses this issue with Implicit Sheaf Operators (ISOs), a type of sheaf topological operators that leverage the topological structure of cellular sheaves to decompose the global diffusion process into local operator-vector products. We mathematically prove that ISO eliminates the $O(md^2 \log(md^2))$ sparse-coalescing term and reduces the space complexity by $O(\min(d, f))$ with respect to traditional Neural Sheaf Diffusion (NSD). Our experiments indicate that ISO-based operators achieve latency reduction of up to 4.87× and save up to 3.92× peak GPU memory. On real graph classification data, ISO uses up to 1.24× less energy and 3.08× less on-device memory as measured on a Jetson Orin Nano. Finally, to bring ISO to practice, we introduce Sheaf Convolutional Networks (SCNs), an ISO-based SNN attaining up to 3.93% higher accuracy compared to NSD-based SNNs on node classification benchmarks.

Implicit Inversion turns CLIP into a Decoder

Thu, 23 Apr 2026 00:00:00 GMT

The Fourteenth International Conference on Learning Representations (ICLR 2026), Poster. Antonio D'Orazio, Maria Rosaria Briglia, Donato Crisostomi, Dario Loi, Emanuele Rodolà, Iacopo Masi.

CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves as the backbone of many generative pipelines, where a decoder is trained to map from the shared space back to images. We show that image synthesis is nevertheless possible using CLIP alone—without a pre-trained generative decoder or CLIP tuning. Our approach optimizes a frequency-aware implicit neural representation that encourages coarse-to-fine generation by stratifying frequencies across network layers. To stabilize this inverse mapping, we introduce adversarially robust initialization, a lightweight Orthogonal Procrustes projection to align local text and image embeddings, and a blending loss that anchors outputs to natural image statistics. With CLIP frozen, this framework unlocks capabilities such as text-to-image generation, style transfer, and image reconstruction. Our findings suggest that discriminative models may hold untapped generative potential, hidden in plain sight.

Topological Deep Learning Challenge 2025: Expanding the Data Landscape

Fri, 27 Feb 2026 00:00:00 GMT

1st Conference on Topology, Algebra, and Geometry in Data Science (TAG-DS 2025). Guillermo Bernárdez, Lev Telyatnikov, Mathilde Papillon, Marco Montagna, Raffael Theiler, Louisa Cornelis, Johan Mathe, Miquel Ferriol, Pavlo Vasylenko, Jan-Willem Van Looy, Lucia Testa, Bruno Neri, Donatella Genovese, Melanie Weber, Amaury Wei, Alessio Devoto, Alexander Weers, Robert Jankowski, Loris Cino, David Leko, Michael Banf, Jonas Müller, Thomas Grapentin, Taejin Paik, Abhijeet Dutta, Hugo Walter, Thomas Vaitses Fontanari, Ali Ghasemi, Dario Loi, Haitz Sáez de Ocáriz Borde, Gabriela Aguilar-Argüello, Giovanni B. da Rosa, Théo Saulus, Eric Rubiel Dolores-Cuenca, Leonardo Di Nino, Pierrick Leroy, Mario Edoardo Pandolfo, Andrea Cavallo, Yu Qin, Pavel Snopov, Amirreza Akbari, Ixchel Meza-Chávez, Louis Van Langendonck, Jared Able, Maria Yuffa Meshcheryakova, Henry Tsay, Luka Benić, Dominik Filipiak, Patrick Liu, Huidong Liang, Alexsandro Santos da Rosa Jr., Tiziana Cattai, Henrique M. Borges, Enrico Grimaldi, Manuel Lecha, Claudio Battiloro, Xuan-Chen Liu, Raj Deshpande, Graham Johnson, Igor Morgunov, Hugo Micheron, Rémi Devaux, Antoine Jardin, Tegan Emerson, Olga Fink, Nina Miolane.

This paper describes the 2025 edition of the Topological Deep Learning Challenge: Expanding the Data Landscape, hosted at the first Topology, Algebra, and Geometry in Data Science (TAG-DS) Conference. This year’s challenge aimed to address the data bottleneck in the field by systematically expanding the ecosystem of Topological Deep Learning (TDL). Powered by TopoBench, the challenge was organized into two primary missions: enriching the data landscape with diverse datasets, and advancing core data infrastructure. In particular, participants were invited to contribute to the open-source platform by implementing new dataset loaders, designing new benchmark tasks, or engineering robust, scalable data pipelines. The initiative successfully yielded 44 qualifying submissions. This paper outlines the scope of the competition and summarizes the key results and findings, highlighting the new resources now available to the TDL community.

AutoBench: Automating LLM Evaluation through Reciprocal Peer Assessment

Sun, 26 Oct 2025 00:00:00 GMT

Preprint, October 2025. Dario Loi, Elena Maria Muià, Federico Siciliano, Giovanni Trappolini, Vincenzo Crisà, Peter Kruger, Fabrizio Silvestri.

We present AutoBench, a fully automated and self-sustaining framework for evaluating Large Language Models (LLMs) through reciprocal peer assessment. This paper provides a rigorous scientific validation of the AutoBench methodology, originally developed as an open-source project by eZecute S.R.L. Unlike static benchmarks that suffer from test-set contamination and limited adaptability, AutoBench dynamically generates novel evaluation tasks while models alternately serve as question generators, contestants, and judges across diverse domains. An iterative weighting mechanism amplifies the influence of consistently reliable evaluators, aggregating peer judgments into consensus-based rankings that reflect collective model agreement. Our experiments demonstrate strong correlations with established benchmarks including MMLU-Pro and GPQA (respectively 78% and 63%), validating this peer-driven evaluation paradigm. The multi-judge design significantly outperforms single-judge baselines, confirming that distributed evaluation produces more robust and human-consistent assessments. AutoBench offers a scalable, contamination-resistant alternative to static benchmarks for the continuous evaluation of evolving language models.

StemSep

Sat, 05 Apr 2025 00:00:00 GMT

A web app that splits an audio file into stems (vocals, drums, bass, guitar, and the rest) with Demucs. Open source, Apache 2.0.

StapleGL

Mon, 24 Apr 2023 00:00:00 GMT

A header-only OpenGL wrapper in modern C++20 with no dependencies: buffers, shaders, textures, and framebuffers as C++ objects. Open source, MIT.

Exposure Fusion

Mon, 12 Dec 2022 00:00:00 GMT

A Python module for fast HDR image processing: it aligns a bracketed set of exposures and blends them into one well-exposed image. Open source, MIT.

Mine-RCNN

Sat, 14 May 2022 00:00:00 GMT

A PyTorch reimplementation of Faster R-CNN, trained to detect entities in the sandbox game Minecraft. Course project, Deep Learning, Sapienza University of Rome.