Equiangular tight frames from group divisible designs
PulseAugur coverage of Equiangular tight frames from group divisible designs — every cluster mentioning Equiangular tight frames from group divisible designs across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New method prevents over-contraction in AI models for long-tailed recognition
Researchers have developed a new method for long-tailed recognition (LTR) that addresses the issue of tail classes being over-contracted in existing neural collapse (NC) approaches. Their technique, controlled partial n…
-
New research details exact calibration for volume-sampled ridge regression
Researchers have published a paper detailing advancements in volume-sampled ridge regression, a statistical technique. The study focuses on the exact calibration and sharp risk geometry within this method, particularly …
-
Tabular foundation models show cross-modality transfer capabilities
Researchers have developed a novel classification pipeline that integrates an Equiangular Tight Frame (ETF) preprocessing step with a tabular foundation model for in-context inference. This unified approach is applied a…