collaborators

7 papers

cs.AI2026

SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents

Kuangshi Ai, Haichao Miao, Kaiyuan Tang +13

Recent advances in large language models (LLMs) have enabled agentic systems to translate natural-language intent into executable scientific visualization (SciVis) tasks. Despite r…

physics.comp-ph2026

A Physics-Informed B-Spline Framework for Continuous Approximation of Flow Data

Junoh Jung, David Lenz, Emil Constantinescu +1

Continuous approximations of flow data are useful for downstream analysis, differentiation, and visualization, but purely data-driven reconstructions do not, in general, preserve t…

cs.LG2026

Fast Amortized Fitting of Scientific Signals Across Time and Ensembles via Transferable Neural Fields

Sophia Zorek, Kushal Vyas, Yuhao Liu +3

Neural fields, also known as implicit neural representations (INRs), offer a powerful framework for modeling continuous geometry, but their effectiveness in high-dimensional scient…

cs.GR2026

SASAV: Self-Directed Agent for Scientific Analysis and Visualization

Jianxin Sun, David Lenz, Tom Peterka +1

With recent advances in frontier multimodal large language models (MLLMs) for data understanding and visual reasoning, the role of LLMs has evolved from passive LLM-as-an-interface…

cs.GR2025

Make the Fastest Faster: Importance Mask Synthesis for Interactive Volume Visualization using Reconstruction Neural Networks

Jianxin Sun, David Lenz, Hongfeng Yu +1

Visualizing a large-scale volumetric dataset with high resolution is challenging due to the substantial computational time and space complexity. Recent deep learning-based image in…

cs.LG2025

Extracting Complex Topology from Multivariate Functional Approximation: Contours, Jacobi Sets, and Ridge-Valley Graphs

Guanqun Ma, David Lenz, Hanqi Guo +2

Implicit continuous models, such as functional models and implicit neural networks, are an increasingly popular method for replacing discrete data representations with continuous,…