32 citations · 53 across the 27 of their papers we have counts for
27 papers
Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching
Cameron Ryan, Vivek Sivaraman Narayanaswamy, Kowshik Thopalli +1
Independently trained neural networks tend to encode the same data with similar latent geometries. These latent geometries are not directly compatible, yet they can be nearly the s…
LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents
Daehong Kim, Haichao Miao, Shusen Liu
Large language model (LLM) agents can now carry out long-horizon technical workflows involving complex tool use, code execution, file edits, and generated artifacts. As agents do m…
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…
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…
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…
Enhancing Accuracy and Parameter-Efficiency of Neural Representations for Network Parameterization
Hongjun Choi, Jayaraman J. Thiagarajan, Ruben Glatt +1
In this work, we investigate the fundamental trade-off regarding accuracy and parameter efficiency in the parameterization of neural network weights using predictor networks. We pr…
Concept Lens: Visually Analyzing the Consistency of Semantic Manipulation in GANs
Sangwon Jeong, Mingwei Li, Matthew Berger +1
As applications of generative AI become mainstream, it is important to understand what generative models are capable of producing, and the extent to which one can predictably contr…
Visualization Literacy of Multimodal Large Language Models: A Comparative Study
Zhimin Li, Haichao Miao, Valerio Pascucci +1
The recent introduction of multimodal large language models (MLLMs) combine the inherent power of large language models (LLMs) with the renewed capabilities to reason about the mul…
Text-based Transfer Function Design for Semantic Volume Rendering
Sangwon Jeong, Jixian Li, Christopher Johnson +2
Transfer function design is crucial in volume rendering, as it directly influences the visual representation and interpretation of volumetric data. However, creating effective tran…
Learning nuclear cross sections across the chart of nuclides with graph neural networks
Hongjun Choi, Sinjini Mitra, Jason Brodksy +6
In this work, we explore the use of deep learning techniques to learn how nuclear cross sections change as we add or remove protons and neutrons. As a proof of principle, we focus…
AVA: Towards Autonomous Visualization Agents through Visual Perception-Driven Decision-Making
Shusen Liu, Haichao Miao, Zhimin Li +3
With recent advances in multi-modal foundation models, the previously text-only large language models (LLM) have evolved to incorporate visual input, opening up unprecedented oppor…
Transformer-Powered Surrogates Close the ICF Simulation-Experiment Gap with Extremely Limited Data
Matthew L. Olson, Shusen Liu, Jayaraman J. Thiagarajan +3
Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated supe…
Instance-wise Linearization of Neural Network for Model Interpretation
Zhimin Li, Shusen Liu, Kailkhura Bhavya +3
Neural network have achieved remarkable successes in many scientific fields. However, the interpretability of the neural network model is still a major bottlenecks to deploy such t…
Topological Data Analysis Guided Segment Anything Model Prompt Optimization for Zero-Shot Segmentation in Biological Imaging
Ruben Glatt, Shusen Liu
Emerging foundation models in machine learning are models trained on vast amounts of data that have been shown to generalize well to new tasks. Often these models can be prompted w…
Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences between Pretrained Generative Models
Matthew L. Olson, Shusen Liu, Rushil Anirudh +3
Generative Adversarial Networks (GANs) are notoriously difficult to train especially for complex distributions and with limited data. This has driven the need for tools to audit tr…
On-the-fly Object Detection using StyleGAN with CLIP Guidance
Yuzhe Lu, Shusen Liu, Jayaraman J. Thiagarajan +2
We present a fully automated framework for building object detectors on satellite imagery without requiring any human annotation or intervention. We achieve this by leveraging the…
"Understanding Robustness Lottery": A Geometric Visual Comparative Analysis of Neural Network Pruning Approaches
Zhimin Li, Shusen Liu, Xin Yu +5
Deep learning approaches have provided state-of-the-art performance in many applications by relying on large and overparameterized neural networks. However, such networks have been…
Reliable Graph Neural Network Explanations Through Adversarial Training
Donald Loveland, Shusen Liu, Bhavya Kailkhura +2
Graph neural network (GNN) explanations have largely been facilitated through post-hoc introspection. While this has been deemed successful, many post-hoc explanation methods have…
Explainable Deep Learning for Uncovering Actionable Scientific Insights for Materials Discovery and Design
Shusen Liu, Bhavya Kailkhura, Jize Zhang +4
The scientific community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite the effectiveness in buildin…
Actionable Attribution Maps for Scientific Machine Learning
Shusen Liu, Bhavya Kailkhura, Jize Zhang +4
The scientific community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite the effectiveness in buildin…
Parallelizing Training of Deep Generative Models on Massive Scientific Datasets
Sam Ade Jacobs, Brian Van Essen, David Hysom +11
Training deep neural networks on large scientific data is a challenging task that requires enormous compute power, especially if no pre-trained models exist to initialize the proce…
Exploring Generative Physics Models with Scientific Priors in Inertial Confinement Fusion
Rushil Anirudh, Jayaraman J. Thiagarajan, Shusen Liu +2
There is significant interest in using modern neural networks for scientific applications due to their effectiveness in modeling highly complex, non-linear problems in a data-drive…
Function Preserving Projection for Scalable Exploration of High-Dimensional Data
Shusen Liu, Rushil Anirudh, Jayaraman J. Thiagarajan +1
We present function preserving projections (FPP), a scalable linear projection technique for discovering interpretable relationships in high-dimensional data. Conventional dimensio…