Related papers: Task-Based Programming for Adaptive Mesh Refinemen…

Computational Fluid Dynamics (CFD) is a major sub-field of engineering. Corresponding flow simulations are typically characterized by heavy computational resource requirements. Often, very fine and complex meshes are required to resolve…

Mixture-of-Experts (MoE) large language models (LLMs) are among the top-performing architectures. The largest models, often with hundreds of billions of parameters, pose significant memory challenges for deployment. Traditional approaches…

Recent large reasoning models (LRMs) have made substantial progress in complex reasoning tasks, yet they often generate lengthy reasoning paths for every query, incurring unnecessary computation and latency. Existing speed-up approaches…

We address the problem of solving mixed random linear equations. We have unlabeled observations coming from multiple linear regressions, and each observation corresponds to exactly one of the regression models. The goal is to learn the…

Simulating space plasma in a global scale is computationally demanding. Modeling different regions with different resolution can save computational resources without compromising too much on simulation accuracy. This thesis examines…

Process optimization for metal additive manufacturing (AM) is crucial to ensure repeatability, control microstructure, and minimize defects. Despite efforts to address this via the traditional design of experiments and statistical process…

The availability of precise and accurate simulation is a limiting factor for interpreting and forecasting data in many fields of science and engineering. Often, one or more distinct simulation software applications are developed, each with…

The advent of Large Language Models (LLM) has reformed the Automatic Speech Recognition (ASR). Prompting LLM with audio embeddings to generate transcriptions becomes the new state-of-the-art ASR. Despite LLMs being trained with an extensive…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, single-model responses often exhibit inconsistencies, hallucinations, and varying quality across different…

High-quality mesh generation is the foundation of accurate finite element analysis. Due to the vast interior vertices search space and complex initial boundaries, mesh generation for complicated domains requires substantial manual…

Large Language Models (LLMs) demonstrate impressive ability in handling reasoning tasks. However, unlike humans who can instinctively adapt their problem-solving strategies to the complexity of task, most LLM-based methods adopt a…

Retrieval Augmented Generation (RAG) has proven to be highly effective in boosting the generative performance of language model in knowledge-intensive tasks. However, existing RAG framework either indiscriminately perform retrieval or rely…

Large Reasoning Language Models (LRLMs or LRMs) demonstrate remarkable capabilities in complex reasoning tasks, but suffer from significant computational inefficiencies due to overthinking phenomena. Existing efficient reasoning methods…

Large Language Model (LLM) based multi-agent systems have shown remarkable performance in various tasks, especially when enhanced through collaborative communication. However, current methods often rely on a fixed number of agents and…

We present a novel approach to automate and optimize anisotropic p-adaptation in high-order h/p solvers using Reinforcement Learning (RL). The dynamic RL adaptation uses the evolving solution to adjust the high-order polynomials. We develop…

Retrieval-Augmented Generation (RAG) improves factual grounding by incorporating external knowledge into language model generation. However, when retrieved context is noisy, unreliable, or inconsistent with the model's parametric knowledge,…

We introduce a reinforcement learning (RL) based adaptive optimization algorithm for aerodynamic shape optimization focused on dimensionality reduction. The form in which RL is applied here is that of a surrogate-based, actor-critic policy…

The existing Retrieval-Augmented Generation (RAG) systems face significant challenges in terms of cost and effectiveness. On one hand, they need to encode the lengthy retrieved contexts before responding to the input tasks, which imposes…

While Large Language Models (LLMs) have significantly advanced code generation efficiency, they face inherent challenges in balancing performance and inference costs across diverse programming tasks. Dynamically selecting the optimal LLM…

We present a new numerical algorithm for the solution of coupled collisional and collisionless systems, based on the block structured adaptive mesh and time refinement strategy (AMR). We describe the issues associated with the…