23 citations · 38 across the 14 of their papers we have counts for
8 papers · 1 filter
Privileged observations enable rapid and reliable policy discovery directly in the physical world
Antonio Terpin, Raffaello D'Andrea
We study how privileged information about a physical system affects the discovery of high-performing policies when training a reinforcement learning agent directly in the physical…
Flow Gym: A framework for the development, benchmarking, training, and deployment of flow-field quantification methods
Francesco Banelli, Antonio Terpin, Alan Bonomi +1
Particle image velocimetry (PIV) and related optical-flow methods are widely used to quantify fluid motion, but their development and evaluation are often hindered by fragmented so…
Particle Image Velocimetry Refinement via Consensus ADMM for Active Fluid Control
Alan Bonomi, Francesco Banelli, Antonio Terpin
Particle Image Velocimetry (PIV) is among the central modalities for measuring flow fields across laboratory, industrial and environmental setting. Traditional PIV approaches typic…
SynthPix: A lightspeed PIV image generator
Antonio Terpin, Alan Bonomi, Francesco Banelli +1
We describe SynthPix, a synthetic image generator for Particle Image Velocimetry (PIV) with a focus on performance and parallelism on accelerators, implemented in JAX. SynthPix pro…
Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers
Panagiotis D. Grontas, Antonio Terpin, Efe C. Balta +2
We introduce an output layer for neural networks that ensures satisfaction of convex constraints. Our approach, net, leverages operator splitting for rapid and reliable projecti…
Gradient-flow SDEs have unique transient population dynamics
Vincent Guan, Joseph Janssen, Nicolas Lanzetti +3
Identifying the drift and diffusion of an SDE from its population dynamics is a notoriously challenging task. Researchers in machine learning and single-cell biology have only been…
Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling
Michal Balcerak, Tamaz Amiranashvili, Antonio Terpin +5
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 ava…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…