2 citations · 2 across the 9 of their papers we have counts for
9 papers
Prospective Compression in Human Abstraction Learning
Leonardo Hernandez Cano, Ivan Zareski, Luisa El Amouri +6
A core challenge in program synthesis is online library learning: the incremental acquisition of reusable abstractions under uncertainty about future task demands. Existing algorit…
Online library learning in human visual puzzle solving
Pinzhe Zhao, Emanuele Sansone, Marta Kryven +1
When learning a novel complex task, people often form efficient reusable abstractions that simplify future work, despite uncertainty about the future. We study this process in a vi…
Can AI Understand the Language of Origami?
Naaisha Agarwal, Yihan Wu, Xin Guan +10
Building AI systems that can plan, act, and create in the physical world requires more than pattern recognition. Such systems must reason about the generative mechanisms and constr…
Power Term Polynomial Algebra for Boolean Logic
Emanuele Sansone, Armando Solar-Lezama
We introduce power term polynomial algebra, a representation language for Boolean formulae designed to bridge conjunctive normal form (CNF) and algebraic normal form (ANF). The lan…
Collapse-Proof Non-Contrastive Self-Supervised Learning
Emanuele Sansone, Tim Lebailly, Tinne Tuytelaars
We present a principled and simplified design of the projector and loss function for non-contrastive self-supervised learning based on hyperdimensional computing. We theoretically…
EXPLAIN, AGREE, LEARN: Scaling Learning for Neural Probabilistic Logic
Victor Verreet, Lennert De Smet, Luc De Raedt +1
Neural probabilistic logic systems follow the neuro-symbolic (NeSy) paradigm by combining the perceptive and learning capabilities of neural networks with the robustness of probabi…
(Deep) Generative Geodesics
Beomsu Kim, Michael Puthawala, Jong Chul Ye +1
In this work, we propose to study the global geometrical properties of generative models. We introduce a new Riemannian metric to assess the similarity between any two data points.…
Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick
Lennert De Smet, Emanuele Sansone, Pedro Zuidberg Dos Martires
Categorical random variables can faithfully represent the discrete and uncertain aspects of data as part of a discrete latent variable model. Learning in such models necessitates t…
The Triad of Failure Modes and a Possible Way Out
Emanuele Sansone
We present a novel objective function for cluster-based self-supervised learning (SSL) that is designed to circumvent the triad of failure modes, namely representation collapse, cl…