Related papers: Colmena: Scalable Machine-Learning-Based Steering …

A key hurdle is demonstrating compute resource capability with limited benchmarks. We propose workflow templates as a solution, offering adaptable designs for specific scientific applications. Our paper identifies common usage patterns for…

Model selection is a strategy aimed at creating accurate and robust models. A key challenge in designing these algorithms is identifying the optimal model for classifying any particular input sample. This paper addresses this challenge and…

We present a Python extension to the massively parallel HPC simulation toolkit waLBerla. waLBerla is a framework for stencil based algorithms operating on block-structured grids, with the main application field being fluid simulations in…

The computational complexity of large language model (LLM) inference significantly constrains their deployment efficiency on edge devices. In contrast, small language models offer faster decoding and lower resource consumption but often…

Recent research on testing autonomous driving agents has grown significantly, especially in simulation environments. The CARLA simulator is often the preferred choice, and the autonomous agents from the CARLA Leaderboard challenge are…

Existing novice-friendly machine learning (ML) modeling tools center around a solo user experience, where a single user collects only their own data to build a model. However, solo modeling experiences limit valuable opportunities for…

Data-driven, machine learning (ML) models of atomistic interactions are often based on flexible and non-physical functions that can relate nuanced aspects of atomic arrangements into predictions of energies and forces. As a result, these…

Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multiple models and selecting the most probable label. This idea…

Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models or smaller specialized models, each with distinct…

Automatic test generation plays a critical role in software quality assurance. While the recent advances in Search-Based Software Testing (SBST) and Large Language Models (LLMs) have shown promise in generating useful tests, these…

Large language models (LLMs) as autonomous agents offer a novel avenue for tackling real-world challenges through a knowledge-driven manner. These LLM-enhanced methodologies excel in generalization and interpretability. However, the…

This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple…

PLUMED is an open-source software package that is widely used for analyzing and enhancing molecular dynamics simulations that works in conjunction with most available molecular dynamics softwares. While the computational cost of PLUMED…

Almost all applications stop scaling at some point; those that don't are seldom performant when considering time to solution on anything but aspirational/unicorn resources. Recognizing these tradeoffs as well as greater user functionality…

Project-Based Learning (PBL) involves a variety of highly correlated multimodal data, making it a vital educational approach within STEM disciplines. With the rapid development of multimodal large language models (MLLMs), researchers have…

Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a lightweight alternative to expensive retraining. However,…

Large Language Models (LLMs) are unable to reliably reason about specific physical systems. Attempts to imbue LLMs with knowledge of the necessary physics concepts have shown great promise, but explainability and validation remain open…

Large Language Models (LLMs) have achieved remarkable performance across various reasoning tasks, yet post-training is constrained by inefficient sample utilization and inflexible difficulty samples processing. To address these limitations,…

While LLMs have demonstrated remarkable capabilities in text generation and reasoning, their ability to simulate human decision-making -- particularly in political contexts -- remains an open question. However, modeling voter behavior…

Classical machine learning (CML) occupies nearly half of machine learning pipelines in production applications. Unfortunately, it fails to utilize the state-of-the-practice devices fully and performs poorly. Without a unified framework, the…