activity
20232026
collaborators

6 papers

cs.AI2026

Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation

Lin Shi, Haowei Lin, Zixuan Zhu +123

Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a…

cs.LG2026

ShapeBench: A Scalable Benchmark and Diagnostic Suite for Standardized Evaluation in Aerodynamic Shape Optimization

Shaghayegh Fazliani, Krissh Chawla, Jack Guo +3

Rapid progress in aerodynamic shape optimization (ASO) has outpaced currently-available standardized evaluation frameworks. Fair comparison requires a unified benchmark spanning di…

cs.LG2025

PDE-SHARP: PDE Solver Hybrids through Analysis and Refinement Passes

Shaghayegh Fazliani, Madeleine Udell

Current LLM-driven approaches using test-time computing to generate PDE solvers execute a large number of solver samples to identify high-accuracy solvers. These paradigms are espe…

cs.LG2025

Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project

Pratik Rathore, Zachary Frangella, Sachin Garg +3

Gaussian processes (GPs) play an essential role in biostatistics, scientific machine learning, and Bayesian optimization for their ability to provide probabilistic predictions and…

cs.LG2025

Enhancing Physics-Informed Neural Networks Through Feature Engineering

Shaghayegh Fazliani, Zachary Frangella, Madeleine Udell

Physics-Informed Neural Networks (PINNs) seek to solve partial differential equations (PDEs) with deep learning. Mainstream approaches that deploy fully-connected multi-layer deep…

math.AP2023

Hausdorff measure bound for the nodal sets of Neumann Laplace eigenfunctions

Shaghayegh Fazliani

We study the nodal sets of Neumann Laplace eigenfunctions in a bounded domain with boundary. We show that for such that with the Neumann…