1 citations · 1 across the 4 of their papers we have counts for
4 papers
Understanding and Reducing Metadata-Driven Host Overheads in Sampling-Based GNN Training
Yidong Gong, Saima Afrin, Yuchen Ma +3
Modern deep learning workloads increasingly exhibit dynamic, metadata-driven execution, where runtime-generated information determines memory provisioning and kernel launch decisio…
Reconstructing Multi-Scale Physical Fields from Extremely Sparse Measurements with an Autoencoder-Diffusion Cascade
Letian Yi, Tingpeng Zhang, Mingyuan Zhou +3
Extreme sensor sparsity makes full-field reconstruction a fundamentally ill-posed problem in scientific sensing,where the goal is to infer physical fields from sparse measurements.…
Training-Free Inference for High-Resolution Sinogram Completion
Jiaze E, Srutarshi Banerjee, Tekin Bicer +3
High-resolution sinogram completion is critical for computed tomography reconstruction, as missing projections can introduce severe artifacts. While diffusion models provide strong…
FCDM: A Physics-Guided Bidirectional Frequency Aware Convolution and Diffusion-Based Model for Sinogram Inpainting
Jiaze E, Srutarshi Banerjee, Tekin Bicer +3
Computed tomography (CT) is widely used in scientific imaging systems such as synchrotron and laboratory-based nano-CT, but acquiring full-view sinograms requires high radiation do…