103 citations · 272 across the 64 of their papers we have counts for
68 papers
MERIT: Scaling KG Foundation Models with Relation Transformers
Cosimo Gregucci, Daniel Hernandez, Antonio Vergari +1
Knowledge graph (KG) foundation models (KGFMs) predict links on unseen graphs zero-shot. KGFMs have been pioneered by ULTRA which builds a relation graph from co-occurrences that m…
When Are Concept Bottleneck Model Explanations Faithful and Compact?
Stefano Teso, Emanuele Marconato, Steve Azzolin +1
Concept bottleneck models (CBMs) are neural classifiers that allow to explain their decisions via high-level concepts, potentially enabling understanding, steering and debugging. H…
Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval
Nickil Maveli, Antonio Vergari, Shay B. Cohen
Large language models (LLMs) have demonstrated strong performance in code generation, where success depends on both recalling relevant algorithmic knowledge and reasoning about how…
The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning
Agnese Chiatti, Michael Cochez, Cristina Cornelio +14
Neurosymbolic AI systems that integrate machine learning and symbolic reasoning are rapidly gaining attention. They complement the data-intensive statistical approaches of neural n…
Neural network surrogates with uncertainty quantification for inverse problems in partial differential equations
Christian Jimenez-Beltran, Aretha L. Teckentrup, Antonio Vergari +1
Inverse problems for differential equations arise throughout science and engineering, where one seeks to infer unknown model parameters from noisy or incomplete observations. Tradi…
Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Models
Cosimo Gregucci, Obaidah Theeb, Daniel Hernandez +2
Knowledge graph (KG) foundation models (KGFMs) are zero-shot generalizers: trained once, they can predict links on unseen graphs without retraining. However, understanding when and…
Tractable Hierarchical Control of Autoregressive Language Models
Max Scribner, Antonio Vergari, Vaishak Belle
Constraining the generation of autoregressive large language models (LLMs) is an important component of integrating language models into formal systems. In the generation of code a…
How to Approximate Inference with Subtractive Mixture Models
Lena Zellinger, Nicola Branchini, Lennert De Smet +3
Classical mixture models (MMs) are widely used tractable proposals for approximate inference settings such as variational inference (VI) and importance sampling (IS). Recently, mix…
MIXAR: Scaling Autoregressive Pixel-based Language Models to Multiple Languages and Scripts
Chen Hu, Yintao Tai, Antonio Vergari +2
Pixel-based language models are gaining momentum as alternatives to traditional token-based approaches, promising to circumvent tokenization challenges; however, existing models re…
Even More Guarantees for Variational Inference in the Presence of Symmetries
Lena Zellinger, Antonio Vergari
When approximating an intractable density via variational inference (VI) the variational family is typically chosen as a simple parametric family that very likely does not contain…
Can VLMs Reason Robustly? A Neuro-Symbolic Investigation
Weixin Chen, Antonio Vergari, Han Zhao
Vision-Language Models (VLMs) have been applied to a wide range of reasoning tasks, yet it remains unclear whether they can reason robustly under distribution shifts. In this paper…
A Sobering Look at Tabular Data Generation via Probabilistic Circuits
Davide Scassola, Dylan Ponsford, Adrián Javaloy +4
Tabular data is more challenging to generate than text and images, due to its heterogeneous features and much lower sample sizes. On this task, diffusion-based models are the curre…
The Theory and Practice of MAP Inference over Non-Convex Constraints
Leander Kurscheidt, Gabriele Masina, Roberto Sebastiani +1
In many safety-critical settings, probabilistic ML systems have to make predictions subject to algebraic constraints, e.g., predicting the most likely trajectory that does not cros…
An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale
Adrián Javaloy, Antonio Vergari
Orthogonality constraints are ubiquitous in robust and probabilistic machine learning. Unfortunately, current optimizers are computationally expensive and do not scale to problems…
To Neuro-Symbolic Classification and Beyond by Compiling Description Logic Ontologies to Probabilistic Circuits
Nicolas Lazzari, Valentina Presutti, Antonio Vergari
Background: Neuro-symbolic methods enhance the reliability of neural network classifiers through logical constraints, but they lack native support for ontologies. Objectives: We ai…
Can LLMs Compress (and Decompress)? Evaluating Code Understanding and Execution via Invertibility
Nickil Maveli, Antonio Vergari, Shay B. Cohen
LLMs demonstrate strong performance on code benchmarks, yet consistent reasoning across forward and backward execution remains elusive. We present RoundTripCodeEval (RTCE), a bench…
How to Square Tensor Networks and Circuits Without Squaring Them
Lorenzo Loconte, Adrián Javaloy, Antonio Vergari
Squared tensor networks (TNs) and their extension as computational graphs--squared circuits--have been used as expressive distribution estimators, yet supporting closed-form margin…
Can LLMs subtract numbers?
Mayank Jobanputra, Nils Philipp Walter, Maitrey Mehta +7
We present a systematic study of subtraction in large language models (LLMs). While prior benchmarks emphasize addition and multiplication, subtraction has received comparatively l…
Fast and Expressive Multi-Byte Prediction with Probabilistic Circuits
Andreas Grivas, Lorenzo Loconte, Emile van Krieken +6
Multi-token prediction (MTP) is a prominent strategy to significantly speed up generation in large language models (LLMs), especially in byte-level LLMs, which are tokeniser-free b…
Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts
Emanuele Marconato, Samuele Bortolotti, Emile van Krieken +6
Neuro-symbolic (NeSy) AI aims to develop deep neural networks whose predictions comply with prior knowledge encoding, e.g. safety or structural constraints. As such, it represents…
Tractable Representation Learning with Probabilistic Circuits
Steven Braun, Sahil Sidheekh, Antonio Vergari +3
Probabilistic circuits (PCs) are powerful probabilistic models that enable exact and tractable inference, making them highly suitable for probabilistic reasoning and inference task…
Neurosymbolic Reasoning Shortcuts under the Independence Assumption
Emile van Krieken, Pasquale Minervini, Edoardo Ponti +1
The ubiquitous independence assumption among symbolic concepts in neurosymbolic (NeSy) predictors is a convenient simplification: NeSy predictors use it to speed up probabilistic r…
SEMMA: A Semantic Aware Knowledge Graph Foundation Model
Arvindh Arun, Sumit Kumar, Mojtaba Nayyeri +4
Knowledge Graph Foundation Models (KGFMs) have shown promise in enabling zero-shot reasoning over unseen graphs by learning transferable patterns. However, most existing KGFMs rely…
Neurosymbolic Diffusion Models
Emile van Krieken, Pasquale Minervini, Edoardo Ponti +1
Neurosymbolic (NeSy) predictors combine neural perception with symbolic reasoning to solve tasks like visual reasoning. However, standard NeSy predictors assume conditional indepen…