4 papers
A Physics-Inspired Optimizer: Velocity Regularized Adam
Pranav Vaidhyanathan, Lucas Schorling, Natalia Ares +1
We introduce Velocity-Regularized Adam (VRAdam), a physics-inspired optimizer for training deep neural networks that draws on ideas from quartic terms for kinetic energy with its s…
RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents
Sonali Goel, Pranav Vaidhyanathan, Lucas Schorling +2
Large language models are increasingly deployed as long-lived agents that must adapt across users, tasks, domains, modalities, and feedback regimes without access to model weights.…
End-to-End Analysis of Charge Stability Diagrams with Transformers
Rahul Marchand, Lucas Schorling, Cornelius Carlsson +8
Transformer models and end-to-end learning frameworks are rapidly revolutionizing the field of artificial intelligence. In this work, we apply object detection transformers to anal…
Meta-learning characteristics and dynamics of quantum systems
Lucas Schorling, Pranav Vaidhyanathan, Jonas Schuff +7
While machine learning holds great promise for quantum technologies, most current methods focus on predicting or controlling a specific quantum system. Meta-learning approaches, ho…