large-scale-data

GEM-KMeans introduces a spectrally normalized, memory-efficient NLR formulation for K-means clustering that fuses updates into a single matrix-multiplication epilogue, reducing GPU HBM storage to one factor while maintaining clustering accuracy at massive scale.

InternW0-Δ is a unified world action model that integrates visual dynamics, semantics, geometry, and actions using a Mixture-of-Transformers framework, pretrained on over 20K hours of open data for robot manipulation. It demonstrates strong performance in simulations and real robots and will be open-sourced.

This paper investigates distributed sketching for OLS regression, where sketches are built from partitioned subsets rather than the whole dataset, reducing computational cost. The authors characterize the exact excess loss of the averaged estimator and show it matches that of whole-data sketching when subset covariance divergence is small.

This paper explores the use of variational autoencoders to learn latent representations of large-scale X-ray scattering data, enabling efficient data compression and analysis.