Computational Engineering Papers of the Week

This study views protein design as a search optimization problem over a combinatorial sequence space under expensive structural evaluation. Toward this goal, we introduce a novel tree-based search framework, ProteoCraft, that employs approximate structural gradients from diffusion-based structure predictors as effective proposal policies to specify where the search should explore.

In the cavity study, hierarchical THB refinement reduces the displacement error in the target inner band by a factor of approximately $41$.

In this paper, we examine how researchers and practitioners can select and apply AI methods in finance.

We present 3D-BBDA, a backpropagation-free black-box domain adaptation framework that adapts a source-trained predictor to unlabeled target data using only black-box outputs.

Here we introduce the Implicit Neural Operator Solver (INOS), which learns the implicit solve and encodes a time integrator.

We introduce Fracture-Bench, an open benchmark of two phase-field datasets with fixed splits, common test metrics and a description of each dataset's physical regime.

We present PaddleMaterials, an open-source framework integrating heterogeneous materials-learning tasks while preserving task-specific representations and scientific semantics.

Here we introduce Energy-Propagated Intrinsic Confidence (EPIC), a general energy-centered evidential framework that derives forces as exact gradients of the predicted mean energy, ensuring conservative force fields while providing an analytical estimate of energy uncertainty.

We present pair_style uma, a LAMMPS pair style that evaluates the Universal Model for Atoms (UMA) through LibTorch on NVIDIA and Intel GPUs from a single source tree.

We formulate data product pricing as a learning task over a heterogeneous information network spanning data products, providers, marketplaces, industries, and pricing modes, and design theory-grounded meta-paths, brand-based, similarity-based, industry-based, and hybrid, to characterize distinct pricing mechanisms. Building on this network, we propose a Meta-Path-Guided Heterogeneous Graph Neural Network (MPGNN), which learns path-specific representations, fuses them through an attention-based gate, and is further augmented with large language model-generated textual features.

We present GURU, a hierarchical neuro-symbolic multi-agent system for mission-critical digital engineering and operations, built on one partition of authority: learned models propose, rank, and accelerate; a symbolic rules engine checks every consequential action against hard limits before it executes; and validated physics confirms and decides.

We present a multifidelity methodology that reduces offline basis-construction costs by combining a small HF database with low-fidelity (LF) solutions.

This work presents a new method for gradient-based optimization of the rhombic transposition flap and the excision it closes, which set the strain of the skin after closure.

This paper will show the traditional financial modelling techniques for spreadsheets can be replaced by radically different approaches that have significant gains in readability, performance and flexibility.

Here we present domain-decomposition attention neural operator (DANO), which learns configuration-dependent interactions in heterogeneous systems governed by linear field equations from field data alone.

Here, we integrate mechanistic simulation, surrogate neural networks, and explainable machine learning to identify key regulatory drivers of polarization.

Operator inference (OpInf) provides a nonintrusive framework for learning projection-based reduced-order models directly from data, but its standard formulations do not explicitly account for the fact that boundary actuation changes the admissible solution space of a PDE.

We evaluated the workflow on 50 author-built topology-optimization briefs, injected faults, five numerical problems, and complete agent sessions.

In this work, we extend the TokaMark benchmark with two groups of tasks for actuator action inversion and disruption prediction, yielding 20 MAST tasks in six groups with explicit schemas and evaluation protocols.

Here we propose a Load- and Geometry-adaptive Deep Operator Network (LG-DON) that integrates global geometric representations with local, boundary-aware information to predict structural responses.