activity
20242026
collaborators

7 papers

cs.CV2026

AsyncPatch Diffusion: spatially-flexible image generation

Samuele Papa, Valentin De Bortoli, Guillaume Couairon +3

Standard diffusion models corrupt an entire sample with a single shared noise level, forcing all spatial regions to follow the same denoising trajectory. We introduce AsyncPatch Di…

cs.RO2025

Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination

Leonardo Barcellona, Andrii Zadaianchuk, Davide Allegro +3

A world model provides an agent with a representation of its environment, enabling it to predict the causal consequences of its actions. Current world models typically cannot direc…

cs.CV2025

Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models

Amir Mohammad Karimi Mamaghan, Samuele Papa, Karl Henrik Johansson +2

Object-centric (OC) representations, which model visual scenes as compositions of discrete objects, have the potential to be used in various downstream tasks to achieve systematic…

cs.LG2025

NeuralDEM -- Real-time Simulation of Industrial Particulate Flows

Benedikt Alkin, Tobias Kronlachner, Samuele Papa +3

Advancements in computing power have made it possible to numerically simulate large-scale fluid-mechanical and/or particulate systems, many of which are integral to core industrial…

cs.LG2025

Grounding Continuous Representations in Geometry: Equivariant Neural Fields

David R Wessels, David M Knigge, Samuele Papa +4

Conditional Neural Fields (CNFs) are increasingly being leveraged as continuous signal representations, by associating each data-sample with a latent variable that conditions a sha…

cs.LG2024

From MLP to NeoMLP: Leveraging Self-Attention for Neural Fields

Miltiadis Kofinas, Samuele Papa, Efstratios Gavves

Neural fields (NeFs) have recently emerged as a state-of-the-art method for encoding spatio-temporal signals of various modalities. Despite the success of NeFs in reconstructing in…