Ruben Glatt
YOU?
Author Swipe
View article: Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models through Reinforcement Learning from Ranking Feedback
Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models through Reinforcement Learning from Ranking Feedback Open
Recent advances in large video-language models (VLMs) rely on extensive fine-tuning techniques that strengthen alignment between textual and visual comprehension. Leading pipelines typically pair supervised fine-tuning (SFT) with reinforce…
View article: Learning nuclear cross sections across the chart of nuclides with graph neural networks
Learning nuclear cross sections across the chart of nuclides with graph neural networks Open
We explore the use of deep learning techniques to learn how nuclear cross sections change as we add or remove protons and neutrons. As a proof of principle, we focus on the neutron-induced reactions in the fast energy regime. Our approach …
View article: Deep Symbolic Optimization: Reinforcement Learning for Symbolic Mathematics
Deep Symbolic Optimization: Reinforcement Learning for Symbolic Mathematics Open
Deep Symbolic Optimization (DSO) is a novel computational framework that enables symbolic optimization for scientific discovery, particularly in applications involving the search for intricate symbolic structures. One notable example is eq…
View article: Safety in Artificial Intelligence: Challenges and Opportunities for the U.S. National Labs and Beyond
Safety in Artificial Intelligence: Challenges and Opportunities for the U.S. National Labs and Beyond Open
This report discusses the importance of the critical and underexplored topic of artificial intelligence (AI) safety, as highlighted during the “Strategy Alignment on AI Safety” workshop convened at Lawrence Livermore National Laboratory (L…
View article: SRBench++: Principled Benchmarking of Symbolic Regression With Domain-Expert Interpretation
SRBench++: Principled Benchmarking of Symbolic Regression With Domain-Expert Interpretation Open
Symbolic regression searches for analytic expressions that accurately describe studied phenomena. The main promise of this approach is that it may return an interpretable model that can be insightful to users, while maintaining high accura…
View article: Enhancing Accuracy and Parameter-Efficiency of Neural Representations for Network Parameterization
Enhancing Accuracy and Parameter-Efficiency of Neural Representations for Network Parameterization Open
In this work, we investigate the fundamental trade-off regarding accuracy and parameter efficiency in the parameterization of neural network weights using predictor networks. We present a surprising finding that, when recovering the origin…
View article: A Review on Simulation Platforms for Agent-Based Modeling in Electrified Transportation
A Review on Simulation Platforms for Agent-Based Modeling in Electrified Transportation Open
As the use of combustion engine vehicles plays a deciding role in global warming, we can observe a trend to replace them with electric vehicles (EV) driven by new environmentally conscious policies and increasing technological capabilities…
View article: AutoTG: Reinforcement Learning-Based Symbolic Optimization for AI-Assisted Power Converter Design
AutoTG: Reinforcement Learning-Based Symbolic Optimization for AI-Assisted Power Converter Design Open
Power converters are pervasive in modern electronic component design. They can be found in all electronic devices from household appliances and cellphone chargers to vehicles. Currently, designing new circuit topologies is hard because it …
View article: Topological Data Analysis Guided Segment Anything Model Prompt Optimization for Zero-Shot Segmentation in Biological Imaging
Topological Data Analysis Guided Segment Anything Model Prompt Optimization for Zero-Shot Segmentation in Biological Imaging Open
Emerging foundation models in machine learning are models trained on vast amounts of data that have been shown to generalize well to new tasks. Often these models can be prompted with multi-modal inputs that range from natural language des…
View article: Deep Reinforcement Learning-Based Optimal Parameter Design of Power Converters
Deep Reinforcement Learning-Based Optimal Parameter Design of Power Converters Open
The optimal design of power converters often requires a long time to process with a huge number of simulations to determine the optimal parameters. To reduce the design cycle, this paper proposes a proximal policy optimization (PPO)-based …
View article: An RMRAC With Deep Symbolic Optimization for DC–AC Converters Under Less-Inertia Power Grids
An RMRAC With Deep Symbolic Optimization for DC–AC Converters Under Less-Inertia Power Grids Open
This paper presents a novel approach for grid-injected current control of DC-AC converters using a robust model reference adaptive controller (RMRAC) with deep symbolic optimization (DSO). Grid voltages are known to be time-varying and can…
View article: GAN-based Data Mapping for Model Adaptation
GAN-based Data Mapping for Model Adaptation Open
Although Machine Learning algorithms are solving tasks of ever-increasing complexity, gathering data and building training sets remains an error prone, costly, and difficult problem.However, reusing knowledge from related previouslysolved …
View article: Improving Exploration in Policy Gradient Search: Application to Symbolic Optimization
Improving Exploration in Policy Gradient Search: Application to Symbolic Optimization Open
Many machine learning strategies designed to automate mathematical tasks leverage neural networks to search large combinatorial spaces of mathematical symbols. In contrast to traditional evolutionary approaches, using a neural network at t…
View article: Deep Neural Network-Based Surrogate Model for Optimal Component Sizing of Power Converters Using Deep Reinforcement Learning
Deep Neural Network-Based Surrogate Model for Optimal Component Sizing of Power Converters Using Deep Reinforcement Learning Open
The optimal design of power converters often requires a huge number of simulations and numeric analyses to determine the optimal parameters. This process is time-consuming and results in a high computational cost. Therefore, this paper pro…
View article: Collaborative energy demand response with decentralized actor and centralized critic
Collaborative energy demand response with decentralized actor and centralized critic Open
The ongoing industrialization and rising technology adoption around the world are leading to ever higher energy consumption. The benefits of electrification are enormous, but the growing demand also comes with challenges with respect to as…
View article: Symbolic Regression via Neural-Guided Genetic Programming Population Seeding
Symbolic Regression via Neural-Guided Genetic Programming Population Seeding Open
Symbolic regression is the process of identifying mathematical expressions that fit observed output from a black-box process. It is a discrete optimization problem generally believed to be NP-hard. Prior approaches to solving the problem i…
View article: Symbolic Regression via Neural-Guided Genetic Programming Population\n Seeding
Symbolic Regression via Neural-Guided Genetic Programming Population\n Seeding Open
Symbolic regression is the process of identifying mathematical expressions\nthat fit observed output from a black-box process. It is a discrete\noptimization problem generally believed to be NP-hard. Prior approaches to\nsolving the proble…
View article: Abmarl: Connecting Agent-Based Simulations with Multi-Agent Reinforcement Learning
Abmarl: Connecting Agent-Based Simulations with Multi-Agent Reinforcement Learning Open
Abmarl is a package for developing Agent-Based Simulations and training them with Multi-Agent Reinforcement Learning (MARL).We provide an intuitive command line interface for engaging with the full workflow of MARL experimentation: trainin…
View article: GAN-based Data Mapping for Model Adaptation
GAN-based Data Mapping for Model Adaptation Open
Although Machine Learning algorithms are solving tasks of ever-increasing complexity, gathering data and building training sets remains an error prone, costly, and difficult problem. However, reusing knowledge from related previously-solve…
View article: Improving exploration in policy gradient search: Application to symbolic optimization
Improving exploration in policy gradient search: Application to symbolic optimization Open
Many machine learning strategies designed to automate mathematical tasks leverage neural networks to search large combinatorial spaces of mathematical symbols. In contrast to traditional evolutionary approaches, using a neural network at t…