Raiven mediates LLM visualization authoring via a formally defined DSL that unifies scientific and information visualization, producing deterministic, verifiable code from metadata-only inputs.
Canonical reference
Title resolution pending
Canonical reference. 83% of citing Pith papers cite this work as background.
14
Pith papers citing it
Background
83% of classified citations
citation-role summary
background 5
extension 1
citation-polarity summary
representative citing papers
Text Encoded Extrusions (TEE) lets LLMs generate and edit manifold 3D meshes by learning sequences of face extrusions from decomposed quadrilateral meshes.
GLUE orchestrates frozen pre-trained generative models into a system-level design generator that enforces feasibility, performance, and diversity, with data-driven and data-free variants benchmarked on UAV design.
A graph-based technique splits ambiguous instances into multiple points in DR projections to reduce partial neighborhood embedding and reveal hidden memberships.
SotA Lens introduces a network-augmented workflow that turns seed searches into citation graphs with community detection to support exploratory state-of-the-art reviews.
EdgeFormer converts point cloud edge detection into local-patch point classification with a transformer and reports competitive results against six baselines.
LandSAR integrates real-time landslide simulations, visualizations, and 3D-printed tangible terrain models to improve situational awareness and engagement for analysts.
A spectral framework for nonlinear DR uses spectral bases plus cross-entropy optimization to create multi-scale embeddings that preserve both global manifold geometry and local neighborhoods while supporting graph-frequency analysis.
A robust containment query for collections of trimmed NURBS surfaces that computes generalized winding numbers directly via adaptive quadrature on solid angle boundary integrals without surface discretization.
A taxonomy and design space for chart annotations synthesized from qualitative coding of 1,800 static real-world examples.
Tabular sequential graphs with amount-based, time-based, and combined grouping reduce nodes and edges for AML analysis, but expert users found a trade-off where stronger node reduction was not always preferred for insight.
Autark is a serverless toolkit that enables rapid prototyping of urban visual analytics systems via domain-aware abstractions and supports more reliable LLM-assisted coding.
VizCopilot integrates topic modeling with document visualization to support user oversight of retrieved context in enterprise chatbots, enabling detection of misalignments and adaptation of prompting strategies.
YAC is a prototype system that uses a tool-calling multi-agent architecture to translate natural language into linked interactive visualizations and filters for biomedical data, with user-adjustable structured output and a domain-expert user study.
citing papers explorer
-
Raiven: LLM-Based Visualization Authoring via Domain-Specific Language Mediation
Raiven mediates LLM visualization authoring via a formally defined DSL that unifies scientific and information visualization, producing deterministic, verifiable code from metadata-only inputs.
-
Learning to Build Shapes by Extrusion
Text Encoded Extrusions (TEE) lets LLMs generate and edit manifold 3D meshes by learning sequences of face extrusions from decomposed quadrilateral meshes.
-
GLUE: Coordinating Pre-Trained Generative Models for System-Level Design
GLUE orchestrates frozen pre-trained generative models into a system-level design generator that enforces feasibility, performance, and diversity, with data-driven and data-free variants benchmarked on UAV design.
-
When One Point Is Not Enough: Addressing Ambiguous Instances in Dimensionality Reduction by Splitting
A graph-based technique splits ambiguous instances into multiple points in DR projections to reduce partial neighborhood embedding and reveal hidden memberships.
-
SotA Lens: A Network-Augmented Methodology and Tool for Exploratory State-of-the-Art Reviews
SotA Lens introduces a network-augmented workflow that turns seed searches into citation graphs with community detection to support exploratory state-of-the-art reviews.
-
EdgeFormer: local patch-based edge detection transformer on point clouds
EdgeFormer converts point cloud edge detection into local-patch point classification with a transformer and reports competitive results against six baselines.
-
LandSAR: Visceralizing Landslide Data for Enhanced Situational Awareness in Immersive Analytics
LandSAR integrates real-time landslide simulations, visualizations, and 3D-printed tangible terrain models to improve situational awareness and engagement for analysts.
-
A Spectral Framework for Multi-Scale Nonlinear Dimensionality Reduction
A spectral framework for nonlinear DR uses spectral bases plus cross-entropy optimization to create multi-scale embeddings that preserve both global manifold geometry and local neighborhoods while supporting graph-frequency analysis.
-
Robust Containment Queries over Collections of Trimmed NURBS Surfaces via Generalized Winding Numbers
A robust containment query for collections of trimmed NURBS surfaces that computes generalized winding numbers directly via adaptive quadrature on solid angle boundary integrals without surface discretization.
-
A Qualitative Analysis of Common Practices in Annotations: A Taxonomy and Design Space
A taxonomy and design space for chart annotations synthesized from qualitative coding of 1,800 static real-world examples.
-
The Balance between Nuance and Clarity: Decluttering Tabular Sequential Graphs to Counter Money Laundering
Tabular sequential graphs with amount-based, time-based, and combined grouping reduce nodes and edges for AML analysis, but expert users found a trade-off where stronger node reduction was not always preferred for insight.
-
Autark: A Serverless Toolkit for Prototyping Urban Visual Analytics Systems
Autark is a serverless toolkit that enables rapid prototyping of urban visual analytics systems via domain-aware abstractions and supports more reliable LLM-assisted coding.
-
VizCopilot: Fostering Appropriate Reliance on Enterprise Chatbots with Context Visualization
VizCopilot integrates topic modeling with document visualization to support user oversight of retrieved context in enterprise chatbots, enabling detection of misalignments and adaptation of prompting strategies.
-
YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discovery
YAC is a prototype system that uses a tool-calling multi-agent architecture to translate natural language into linked interactive visualizations and filters for biomedical data, with user-adjustable structured output and a domain-expert user study.