Related papers: Low-EFFourth: A computational framework for genera…
We introduce a generative learning framework to model high-dimensional parametric systems using gradient guidance and virtual observations. We consider systems described by Partial Differential Equations (PDEs) discretized with structured…
The rapid growth of interest in large language models (LLMs) reflects their potential for flexibility and generalization, and attracted the attention of a diverse range of researchers. However, the advent of these techniques has also…
We present a framework for specifying, training, evaluating, and deploying machine learning models. Our focus is on simplifying cutting edge machine learning for practitioners in order to bring such technologies into production. Recognizing…
The remarkable flexibility and adaptability of both deep learning models and ensemble methods have led to the proliferation for their application in understanding many physical phenomena. Traditionally, these two techniques have largely…
This study introduces LLM4DESIGN, a highly automated system for generating architectural and environmental design proposals. LLM4DESIGN, relying solely on site conditions and design requirements, employs Multi-Agent systems to foster…
Deploying large language models (LLMs) in mobile and edge computing environments is constrained by limited on-device resources, scarce wireless bandwidth, and frequent model evolution. Although edge-cloud collaborative inference with…
Video-based Affective Computing (VAC), vital for emotion analysis and human-computer interaction, suffers from model instability and representational degradation due to complex emotional dynamics. Since the meaning of different emotional…
The progression of scientific computing resources has enabled the numerical approximation of mathematical models describing complex physical phenomena. A significant portion of researcher time is typically dedicated to the development of…
A numerical framework is developed to solve various types of PDEs on complicated domains, including steady and time-dependent, non-linear and non-local PDEs, with different boundary conditions that can also include non-linear and non-local…
ML4Chem is an open-source machine learning library for chemistry and materials science. It provides an extendable platform to develop and deploy machine learning models and pipelines and is targeted to the non-expert and expert users.…
Adaptive Computing is an application-agnostic outer loop framework to strategically deploy simulations and experiments to guide decision making for scale-up analysis. Resources are allocated over successive batches, which makes the…
Exploring molecular energy landscapes and identifying ground-state conformations are central challenges in computational chemistry. However, generating diverse low-energy conformers from molecular graphs remains expensive with traditional…
The global energy system is undergoing a major transformation. Renewable energy generation is growing and is projected to accelerate further with the global emphasis on decarbonization. Furthermore, distributed generation is projected to…
This paper introduces HiFloat4 (HiF4), a block floating-point data format tailored for deep learning. Each HiF4 unit packs 64 4-bit elements with 32 bits of shared scaling metadata, averaging 4.5 bits per value. The metadata specifies a…
Organizations and enterprises across domains such as healthcare, finance, and scientific research are increasingly required to extract collective intelligence from distributed, siloed datasets while adhering to strict privacy, regulatory,…
We present a local-to-global and measure-theoretical approach to understanding datasets. The core idea is to formulate a logifold structure and to interpret network models with restricted domains as local charts of datasets. In particular,…
Template-based and LLM-based code generation are both key enablers of automated software development. The former provides correctness guarantees but are rigid for complex requirements, whereas LLMs offer high flexibility at the risk of…
Deep ensemble is a simple yet powerful way to improve the performance of deep neural networks. Under this motivation, recent works on mode connectivity have shown that parameters of ensembles are connected by low-loss subspaces, and one can…
In recent years, machine learning has established itself as a powerful tool for high-resolution weather forecasting. While most current machine learning models focus on deterministic forecasts, accurately capturing the uncertainty in the…
A distributed logic programming language with support for meta-programming and stream processing offers a variety of interesting research problems, such as: How can a versatile and stable data structure for the indexing of a large number of…