collaborators

11 papers

cs.LG2026

Towards Diverse and Comprehensive Benchmarks for Mutual Information Estimation

Alberto Foresti, Ivan Butakov, Alexander Tolmachev +3

Mutual information (MI) estimation is a central problem in machine learning and statistics; however, existing benchmarks typically evaluate estimators on simplified, low-dimensiona…

cs.CV2026

DrivingVoxels: Compositional Sparse Voxel Rasterization for Dynamic Driving Scene Reconstruction

Tania Aguirre, Luis Roldão, Moussab Bennehar +4

Reconstructing dynamic urban scenes remains challenging due to the unbounded nature of driving environments and the presence of multiple dynamic objects. Currently, potentially fas…

cs.LG2026

DIPHINE: Diffusion-based -ID Neural Estimator

Simon Pedro Galeano Munoz, Mustapha Bounoua, Giulio Franzese +2

Uncovering the true informational architecture of real-world complex systems requires disentangling how their components uniquely store, redundantly share, and synergistically inte…

cs.LG2026

Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference

Chao Wang, Luca Nepote, Giulio Franzese +1

Trajectory Inference (TI) seeks to recover latent dynamical processes from snapshot data, where only independent samples from time-indexed marginals are observed. In applications s…

cs.LG2026

TENDE: Transfer Entropy Neural Diffusion Estimation

Simon Pedro Galeano Munoz, Mustapha Bounoua, Giulio Franzese +2

Transfer entropy measures directed information flow in time series, and it has become a fundamental quantity in applications spanning neuroscience, finance, and complex systems ana…

cs.LG2026

Improved Sampling Schedules for Discrete Diffusion Models

Alberto Foresti, Mustapha Bounoua, Giulio Franzese +2

Discrete diffusion models have emerged as a powerful paradigm for generative modeling on sequence data; however, the information-theoretic principles governing their reverse proces…