6 papers
Neural Residual Modeling for Scientific Data Compression under Guaranteed Error Bounds
Surya Majumder, Liangji Zhu, Sanjay Ranka +1
Lossy compression of scientific simulation data increasingly relies on learned, latent-space architectures such as Residual Vector Quantization (RVQ), which iteratively quantize a…
Multivariate Scientific Data Compression with Learned Cross-Variable Latent Decorrelation and Autoregressive Entropy Modeling
Liangji Zhu, Anand Rangarajan, Sanjay Ranka
Scientific simulations generate collections of physical fields with heterogeneous statistics and dependencies, yet learned compressors often encode those fields independently or re…
QoI-Aware Provisional Rollout and Retrospective Reconciliation for Reduced-State Scientific Twins
Liangji Zhu, Scott Klasky, Jaemoon Lee +3
Scientific twins may need to continue operating when updates from an authoritative primary system are temporarily unavailable. Once synchronization resumes, the new boundary can al…
Residual Modeling for High-Fidelity Learned Compression of Scientific Data
Liangji Zhu, Sanjay Ranka, Anand Rangarajan
Lossy compression is essential for massive spatiotemporal data from scientific simulations. Learned compressors can achieve high compression ratios at moderate accuracy targets, bu…
Generative Latent Diffusion for Efficient Spatiotemporal Data Reduction
Xiao Li, Liangji Zhu, Anand Rangarajan +1
Generative models have demonstrated strong performance in conditional settings and can be viewed as a form of data compression, where the condition serves as a compact representati…
Guaranteed Conditional Diffusion: 3D Block-based Models for Scientific Data Compression
Jaemoon Lee, Xiao Li, Liangji Zhu +2
This paper proposes a new compression paradigm -- Guaranteed Conditional Diffusion with Tensor Correction (GCDTC) -- for lossy scientific data compression. The framework is based o…