activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems

Nicolas Zilberstein, Morteza Mardani, Santiago Segarra

Image restoration faces a fundamental tradeoff: methods that minimize error produce blurry reconstructions, while those that maximize perceptual quality yield sharp but less faithf…

cs.LG2025

Model-Driven Graph Contrastive Learning

Ali Azizpour, Nicolas Zilberstein, Santiago Segarra

We propose , a model-driven graph contrastive learning (GCL) framework that leverages graphons (probabilistic generative models for graphs) to guide contrastive lear…

cs.LG2025

Graph Guided Diffusion: Unified Guidance for Conditional Graph Generation

Victor M. Tenorio, Nicolas Zilberstein, Santiago Segarra +1

Diffusion models have emerged as powerful generative models for graph generation, yet their use for conditional graph generation remains a fundamental challenge. In particular, gui…

cs.LG2024

Learning state and proposal dynamics in state-space models using differentiable particle filters and neural networks

Benjamin Cox, Santiago Segarra, Victor Elvira

State-space models are a popular statistical framework for analysing sequential data. Within this framework, particle filters are often used to perform inference on non-linear stat…

cs.LG2024

Repulsive Latent Score Distillation for Solving Inverse Problems

Nicolas Zilberstein, Morteza Mardani, Santiago Segarra

Score Distillation Sampling (SDS) has been pivotal for leveraging pre-trained diffusion models in downstream tasks such as inverse problems, but it faces two major challenges: $(i)…