collaborators

7 papers

cs.LG2026

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…

cs.AI2026

On the Theoretical Limitations of Embedding-based Link Prediction

Samy Badreddine, Emile van Krieken, Luciano Serafini

Neural networks often map low-dimensional embeddings to high-dimensional output spaces. Usually, the output layer is linear, which can create a "rank bottleneck" that limits the fu…

cs.LG2026

Gradient-Based Optimization on Gödel Logic as Discrete Local Search

Alessandro Daniele, Emile van Krieken

A fundamental challenge in neurosymbolic systems is applying continuous gradient-based optimization to discrete logical domains. While fuzzy relaxations provide differentiability,…

cs.AI2026

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…

cs.CL2025

From KMMLU-Redux to KMMLU-Pro: A Professional Korean Benchmark Suite for LLM Evaluation

Seokhee Hong, Sunkyoung Kim, Guijin Son +3

The development of Large Language Models (LLMs) requires robust benchmarks that encompass not only academic domains but also industrial fields to effectively evaluate their applica…

cs.LG2025

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…