DiffUNet^2: Bidirectional Prediction, Probabilistic Generation and Collaborative Visual Discovery for Scientific Data
2026-06-02 • Human-Computer Interaction
Human-Computer InteractionMachine Learning
AI summaryⓘ
The authors created a new method to better understand how scientific systems change over time by using a special model called DiffUNet². This model can predict many possible futures or pasts, not just one, and lets users explore different scenarios interactively. They built a tool that helps scientists test ideas and compare different timelines by editing states and navigating through possible outcomes. The authors tested their method on various scientific data and found it useful for real scientific analysis.
temporal evolutiondiffusion modelconditional generationvisual analyticsbranching timelinesstate editingprobability-space navigationscientific workflowshypothesis exploration
Authors
Mengdi Chu, Jiaxin Yang, Angus G. Forbes, Nathan Debardeleben, Earl Lawrence, Ayan Biswas, Han-Wei Shen
Abstract
Modeling temporal evolution is important to analyzing and reasoning about scientific phenomena, yet most machine learning methods provide deterministic forward predictions that overlook multiple plausible outcomes and rarely support backward reasoning, limiting their usefulness in practical scientific workflows. We present a framework that integrates diffusion-based generative modeling with interactive visual analytics for scientific exploration. We introduce DiffUNet^2, a conditional diffusion model that enables bidirectional, any-to-any generation across time and captures distributions of plausible system evolutions. Built upon the model, our interactive system supports branching timeline exploration, user-guided state editing, and probability-space navigation, enabling scientists to actively explore alternative hypotheses rather than passively observe predictions. We evaluate the model on 5 datasets across different scientific domains to validate its predictive accuracy and probability-space ensemble quality. In collaboration with domain experts, we demonstrate the effectiveness of our approach in supporting practical scientific temporal data analysis workflows. By integrating modeling and visual interaction, our approach enables scientists to interactively explore system dynamics, transforming generative models into tools for hypothesis-driven scientific analysis.