Related papers: SwarmThinkers: Learning Physically Consistent Atom…

We address the challenge of training diffusion models to sample from unnormalized energy distributions in the absence of data, the so-called diffusion samplers. Although these approaches have shown promise, they struggle to scale in more…

Pre-trained machine learning (ML) models have shown great performance for a wide range of applications, in particular in natural language processing (NLP) and computer vision (CV). Here, we study how pre-training could be used for…

In continual learning, solving the catastrophic forgetting problem may make the models fall into the stability-plasticity dilemma. Moreover, inter-task confusion will also occur due to the lack of knowledge exchanges between different…

Wave Energy Converters, particularly point absorbers, have emerged as one of the most promising technologies for harvesting ocean wave energy. Nevertheless, achieving high conversion efficiency remains challenging due to the inherently…

Foundation models have rapidly advanced AI, raising the question of whether their decisions will ultimately surpass human strategies in real-world domains. The exponential, and possibly super-exponential, pace of AI development makes such…

Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and…

Modern parallel computing devices, such as the graphics processing unit (GPU), have gained significant traction in scientific and statistical computing. They are particularly well-suited to data-parallel algorithms such as the particle…

It was recently demonstrated that a simple Monte Carlo (MC) algorithm involving the swap of particle pairs dramatically accelerates the equilibrium sampling of simulated supercooled liquids. We propose two numerical schemes integrating the…

Transfer reinforcement learning aims to improve the sample efficiency of solving unseen new tasks by leveraging experiences obtained from previous tasks. We consider the setting where all tasks (MDPs) share the same environment dynamic…

Scalable and efficient numerical simulations continue to gain importance, as computation is firmly established as the third pillar of discovery, alongside theory and experiment. Meanwhile, the performance of computing hardware grows through…

The development of powerful numerical techniques has drastically improved our understanding of quantum matter out of equilibrium. Inspired by recent progress in the area of noisy intermediate-scale quantum devices, this paper highlights…

All-atom dynamics simulations are an indispensable quantitative tool in physics, chemistry, and materials science, but large systems and long simulation times remain challenging due to the trade-off between computational efficiency and…

Despite the growing prevalence of large language model (LLM) architectures, a crucial concern persists regarding their energy and power consumption, which still lags far behind the remarkable energy efficiency of the human brain. Recent…

Simulation-based inference (SBI) is constantly in search of more expressive and efficient algorithms to accurately infer the parameters of complex simulation models. In line with this goal, we present consistency models for posterior…

The rapid advancement of large-scale cosmological simulations has opened new avenues for cosmological and astrophysical research. However, the increasing diversity among cosmological simulation models presents a challenge to the robustness.…

In the span of four decades, quantum computation has evolved from an intellectual curiosity to a potentially realizable technology. Today, small-scale demonstrations have become possible for quantum algorithmic primitives on hundreds of…

Molecular Dynamics (MD) simulations are essential for understanding the atomic-level behavior of molecular systems, giving insights into their transitions and interactions. However, classical MD techniques are limited by the trade-off…

Learning various motor skills for quadrupedal robots is a challenging problem that requires careful design of task-specific mathematical models or reward descriptions. In this work, we propose to learn a single capable policy using deep…

Time domain simulation, i.e., modeling the system's evolution over time, is a crucial tool for studying and enhancing power system stability and dynamic performance. However, these simulations become computationally intractable for…

Spiking Neural Networks (SNNs), providing more realistic neuronal dynamics, have been shown to achieve performance comparable to Artificial Neural Networks (ANNs) in several machine learning tasks. Information is processed as spikes within…