3 papers
cs.AI2026
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…
cs.LG2025
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…
cs.LG2025
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…