Google Scholar

Machine learning conferences#

  • Normalized Energy Models for Linear Inverse Problems — Nicolas Zilberstein, Santiago Segarra, Eero Simoncelli, Florentin Guth
    Intl. Conf. on Machine Learning (ICML) 2026 [paper] [code]
  • Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems — Nicolas Zilberstein, Morteza Mardani, Santiago Segarra
    Advances in Neural Inf. Process. Syst. (NeurIPS) 2026 [paper] [code]
  • Repulsive Latent Score Distillation for Solving Inverse Problems — Nicolas Zilberstein, Morteza Mardani, Santiago Segarra
    Intl. Conf. Learn. Repr. (ICLR) 2025 [paper] [code]
  • Scalable Implicit Graphon Learning — Ali Azizpour, Nicolas Zilberstein, Santiago Segarra
    Intl. Conf. on Artif. Intell. and Stat. (AISTATS) 2025

Journals#

  • Graph Guided Diffusion: Unified Guidance for Conditional Graph Generation — Victor M. Tenorio, Nicolas Zilberstein, Santiago Segarra, Antonio G. Marques
    Under Review - IEEE Trans. Signal Inf. Process. Netw. 2026
  • Solving Linear Inverse Problems using Higher-Order Annealed Langevin Diffusion — Nicolas Zilberstein, Ashutosh Sabharwal, Santiago Segarra
    IEEE Trans. Signal Process. 2024
  • Unsupervised learning of sampling distributions for particle filters — Fernando Gama, Nicolas Zilberstein, Martin Sevilla, Richard G Baraniuk, Santiago Segarra
    IEEE Trans. Signal Process. 2023
  • Annealed Langevin dynamics for massive MIMO detection — Nicolas Zilberstein, Chris Dick, Rahman Doost-Mohammady, Ashutosh Sabharwal, Santiago Segarra
    IEEE Trans. Wireless Commun. 2022
  • A BCS microwave imaging algorithm for object detection and shape reconstruction tested with experimental data — Nicolas Zilberstein, Juan Augusto Maya, Andres Altieri
    Electr. Lett. 2021

Signal processing conferences#

  • Prior-informed Flow Matching for Graph Reconstruction — Haoming Chen, Nicolas Zilberstein, Santiago Segarra
    Under Review 2026 [paper] [code]
  • Sampling with Shielded Langevin Monte Carlo Using Navigation Potentials — Nicolas Zilberstein, Santiago Segarra, Luiz Chamon
    Asilomar Conf. Si`nals, Syst. and Comp. (ASILOMAR) 2025 [paper]
  • Joint channel estimation and data detection in massive MIMO systems based on diffusion models — Nicolas Zilberstein, Ananthram Swami, Santiago Segarra
    IEEE Intl. Conf. Acoust., Speech and Signal Process. (ICASSP) 2024
  • End-to-end learning of Gaussian mixture proposals using differentiable particle filters and neural networks — Benjamin Cox, Sara Perez-Vieites, Nicolas Zilberstein, Martin Sevilla, Santiago Segarra, Victor Elvira
    IEEE Intl. Conf. Acoust., Speech and Signal Process. (ICASSP) 2024
  • Accelerated massive MIMO detector based on annealed underdamped Langevin dynamics — Nicolas Zilberstein, Chris Dick, Rahman Doost-Mohammady, Ashutosh Sabharwal, Santiago Segarra
    IEEE Intl. Conf. Acoust., Speech and Signal Process. (ICASSP) 2023
  • State and Dynamics Estimation with the Kalman–Langevin filter — Martin Sevilla*, Nicolas Zilberstein*, Benjamin Cox, Sara Perez-Vieites, Victor Elvira, Santiago Segarra
    Asilomar Conf. Signals, Syst. and Comp. (ASILOMAR) 2023
  • Accelerated massive MIMO detector based on annealed underdamped Langevin dynamics — Nicolas Zilberstein, Chris Dick, Rahman Doost-Mohammady, Ashutosh Sabharwal, Santiago Segarra
    Graph Signal Processing Workshop 2023
  • Detection by Sampling: Massive MIMO Detector based on Langevin Dynamics — Nicolas Zilberstein, Chris Dick, Rahman Doost-Mohammady, Ashutosh Sabharwal, Santiago Segarra
    European Signal Process. Conf. (EUSIPCO) 2022 [doi]
  • Robust MIMO detection using hypernetworks with learned regularizers — Nicolas Zilberstein, Chris Dick, Rahman Doost-Mohammady, Ashutosh Sabharwal, Santiago Segarra
    European Signal Process. Conf. (EUSIPCO) 2022
  • Unrolling Particles: Unsupervised Learning of Sampling Distributions — Fernando Gama, Nicolas Zilberstein, Richard G Baraniuk, Santiago Segarra
    IEEE Intl. Conf. Acoust., Speech and Signal Process. (ICASSP) 2022
  • Particle filter with unknown noise statistics and with prior knowledge — Nicolas Zilberstein, Bruno Cernuschi-Frias
    2018 Argentine Conference on Automatic Control (AADECA) 2018

Workshops#

  • Topology Preserving Regularization for Independent Training of Inter-operable Models — Nicolas Zilberstein, Akshay Malhotra, Yugeswar Deenoo, Shahab Hamidi-Rad
    NeurIPS workshop UniReps 2024

Preprints#

  • Model-Driven Graph Contrastive Learning — Ali Azizpour, Nicolas Zilberstein, Santiago Segarra
    arXiv preprint arXiv:2506.06212 2025

Patents#

Systems and methods for statistics based and topology based interoperable AI/ML model monitoring — Akshay Malhotra, Yugeswar Deenoo, Nicolas Zilberstein, Shahab Hamidi-Rad, Mohamed Salah Ibrahim. InterDigital, US Patent Ref. 18889096, 2024.