Petros Koumoutsakos — accepted AI-conference papers

2025

Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling

Michal Balcerak, Tamaz Amiranashvili, Antonio Terpin, Suprosanna Shit, Lea Bogensperger, Sebastian Kaltenbach +2

NeurIPS 2025poster

Current state-of-the-art generative models map noise to data distributions by matching flows or scores. A key limitation of these models is their inability to readily integrate available partial observations and additional priors. In contrast, energy-based models (EBMs) address this by incorporating…

Cited by 0 Source ↗Scholar ↗

2024

Physics-Regularized Multi-Modal Image Assimilation for Brain Tumor Localization

Michal Balcerak, Tamaz Amiranashvili, Andreas Wagner, Jonas Weidner, Petr Karnakov, Johannes C. Paetzold +4

NeurIPS 2024poster

Physical models in the form of partial differential equations serve as important priors for many under-constrained problems. One such application is tumor treatment planning, which relies on accurately estimating the spatial distribution of tumor cells within a patient’s anatomy. While medical imagi…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2019

Remember and Forget for Experience Replay

Guido Novati, Petros Koumoutsakos

ICML 2019oral

Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the accuracy of such updates may deteriorate when the policy diverg…

Cited by 129 Source ↗PDF ↗code ↗Scholar ↗

2018

ContextVP: Fully Context-Aware Video Prediction

Wonmin Byeon, Qin Wang, Rupesh Kumar Srivastava, Petros Koumoutsakos

ECCV 2018poster

Video prediction models based on convolutional networks, recurrent networks, and their combinations often result in blurry predictions. We identify an important contributing factor for imprecise predictions that has not been studied adequately in the literature: blind spots, i.e., lack of access to…

Cited by 194 Source ↗PDF ↗Scholar ↗