activity
20242026
collaborators

8 papers

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.LG2026

Prior-Informed Flow Matching for Graph Reconstruction

Harvey Chen, Nicolas Zilberstein, Santiago Segarra

We introduce \textit{Prior-Informed Flow Matching (PIFM)}, a conditional flow model for graph reconstruction. Reconstructing graphs from partial observations remains a key challeng…

cs.LG2026

Learning Normalized Energy Models for Linear Inverse Problems

Nicolas Zilberstein, Santiago Segarra, Eero Simoncelli +1

Generative diffusion models can provide powerful prior probability models for inverse problems in imaging, but existing implementations suffer from two key limitations: the p…

stat.CO2025

Sampling with Shielded Langevin Monte Carlo Using Navigation Potentials

Nicolas Zilberstein, Santiago Segarra, Luiz Chamon

We introduce shielded Langevin Monte Carlo (LMC), a constrained sampler inspired by navigation functions, capable of sampling from unnormalized target distributions defined over pu…

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…