8 papers
Backward-Consistent Diffusion Sampling for Sparsely Observed PDE Inverse Problems
Yida Pan, Muhammad H. Ashiq, Chanyong Jung +4
Recovering Partial Differential Equation (PDE) coefficient fields from extremely sparse observations is a severely ill-posed inverse problem for which generative machine learning m…
Imaging-101: Benchmarking LLM Coding Agents on Scientific Computational Imaging
Siyi Chen, Jiahe Ying, Yixuan Jia +9
Computational imaging, which recovers hidden signals from indirect, noisy measurements, underpins quantitative discovery across scientific disciplines, yet building a correct recon…
Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation
Siyi Chen, Shaowei Liu, Yixuan Jia +4
Recent progress has shown promise in distilling multi-step video diffusion models into efficient few-step students. Among them, Distribution Matching Distillation (DMD) and its suc…
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
Xiao Li, Yixuan Jia, Zekai Zhang +6
Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these tw…
ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing
Yixuan Jia, Siyi Chen, Yida Pan +9
Data assimilation (DA) estimates the state of an evolving dynamical system from noisy, partial observations, and is widely used in scientific simulation as well as weather and clim…
MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
Xiang Li, Yixuan Jia, Xiao Li +3
Diffusion models achieve strong generative performance but often rely on classifier-free guidance (CFG), an inference-time intervention that modifies the sampling trajectory. Since…
FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation
Siyi Chen, Yixuan Jia, Qing Qu +2
Data assimilation (DA) integrates observations with a dynamical model to estimate states of PDE-governed systems. Model-driven methods (e.g., Kalman, particle) presuppose full know…
Shorter SPECT Scans Using Self-supervised Coordinate Learning to Synthesize Skipped Projection Views
Zongyu Li, Yixuan Jia, Xiaojian Xu +3
Purpose: This study addresses the challenge of extended SPECT imaging duration under low-count conditions, as encountered in Lu-177 SPECT imaging, by developing a self-supervised l…