activity
20242026
collaborators
Showing cs.AIShow all

6 papers · 1 filter

cs.AI2026

Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning -- The Limit of the Scaling Law

Tiansi Dong, Mateja Jamnik, Pietro Liò

By promoting vectors to spheres and enabling explicit model construction, neural networks can perform symbolic-level syllogistic reasoning without training data. We identify two fu…

cs.AI2026

Actionable Interpretability Must Be Defined in Terms of Symmetries

Pietro Barbiero, Mateo Espinosa Zarlenga, Francesco Giannini +4

This paper argues that interpretability research in Artificial Intelligence (AI) is fundamentally ill-posed as existing definitions of interpretability fail to describe how interpr…

cs.AI2026

A Matter of Interest: Understanding Interestingness of Math Problems in Humans and Language Models

Shubhra Mishra, Yuka Machino, Gabriel Poesia +9

The evolution of mathematics is shaped importantly by interestingness: researchers choose which problems to pursue, and students choose which problems to engage with, based on expe…

cs.AI2026

An AI Monkey Gets Grapes for Sure -- Sphere Neural Networks for Reliable Decision-Making

Tiansi Dong, Henry He, Pietro Liò +1

This paper compares three methodological categories of neural reasoning: LLM reasoning, supervised learning-based reasoning, and explicit model-based reasoning. LLMs remain unrelia…

cs.AI2025

Oruga: An Avatar of Representational Systems Theory

Daniel Raggi, Gem Stapleton, Mateja Jamnik +3

Humans use representations flexibly. We draw diagrams, change representations and exploit creative analogies across different domains. We want to harness this kind of power and end…

cs.AI2025

Sphere Neural-Networks for Rational Reasoning

Tiansi Dong, Mateja Jamnik, Pietro Liò

The success of Large Language Models (LLMs), e.g., ChatGPT, is witnessed by their planetary popularity, their capability of human-like communication, and also by their steadily imp…