13 papers
VETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics Reasoning
Yingbo Ma, Kuangshi Ai, Gordon Dai +3
Visual agents for symbolic graphics reasoning depend on executable world representations, yet continued improvement remains bottlenecked by ambiguous supervision from final renders…
HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualization
Kuangshi Ai, Patrick Phuoc Do, Chaoli Wang
Large language model (LLM) agents enable natural language interaction for scientific visualization (SciVis). Still, prior systems have essentially prioritized autonomy over human a…
SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and Visualization
Kuangshi Ai, Haichao Miao, Kaiyuan Tang +2
Recent advances in agentic visualization have enabled the translation of natural language into executable scientific visualization (SciVis) workflows. While general-purpose coding…
Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization Tasks
Haichao Miao, Zhimin Li, Kuangshi Ai +4
The ability to inspect, interpret, and communicate complex data is crucial for virtually any scientific endeavor, but often requires significant expertise outside the core domain r…
Leveraging Multimodal LLMs for Built Environment and Housing Attribute Assessment from Street-View Imagery
Siyuan Yao, Siavash Ghorbany, Kuangshi Ai +6
We present a novel framework for automatically evaluating building conditions nationwide in the United States by leveraging large language models (LLMs) and Google Street View (GSV…
Exploring LLM Agent Designs and Interaction Modalities for Scientific Visualization
Jackson Vonderhorst, Kuangshi Ai, Haichao Miao +2
This paper examines how large language model (LLM) agents perform on scientific visualization (SciVis) tasks that require generating visualization workflows from natural-language i…
SVLAT: Scientific Visualization Literacy Assessment Test
Patrick Phuoc Do, Kaiyuan Tang, Kuangshi Ai +1
Scientific visualization (SciVis) has become an essential means for exploring, understanding, and communicating complex scientific phenomena. However, the field still lacks a valid…
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…
KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance
Kuangshi Ai, Jonathan A. Karr, Meng Jiang +2
We present Knowledge Extraction on OMIn (KEO), a domain-specific knowledge extraction and reasoning framework with large language models (LLMs) in safety-critical contexts. Using t…
An Evaluation-Centric Paradigm for Scientific Visualization Agents
Kuangshi Ai, Haichao Miao, Zhimin Li +2
Recent advances in multi-modal large language models (MLLMs) have enabled increasingly sophisticated autonomous visualization agents capable of translating user intentions into dat…
TexGS-VolVis: Expressive Scene Editing for Volume Visualization via Textured Gaussian Splatting
Kaiyuan Tang, Kuangshi Ai, Jun Han +1
Advancements in volume visualization (VolVis) focus on extracting insights from 3D volumetric data by generating visually compelling renderings that reveal complex internal structu…
NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splatting
Kuangshi Ai, Kaiyuan Tang, Chaoli Wang
Traditional volume visualization (VolVis) methods, like direct volume rendering, suffer from rigid transfer function designs and high computational costs. Although novel view synth…
Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learning
Simret Araya Gebreegziabher, Kuangshi Ai, Zheng Zhang +2
Active Learning (AL) allows models to learn interactively from user feedback. This paper introduces a counterfactual data augmentation approach to AL, particularly addressing the s…