HASTE enables training-free dynamic compression of pre-trained CNNs by patch-wise LSH-based merging of redundant channels, reporting 46.2% FLOPs reduction on ResNet34 CIFAR-10 with 1.25% accuracy drop.
Database-friendly random projections: Johnson-lindenstrauss with binary coins.Journal of Computer and System Sciences, 66(4):671 – 687
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
baseline 1
method 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5representative citing papers
MACROCAST is the first leakage-free time series foundation model for real-time macroeconomic forecasting, trained exclusively on synthetic series and vintage data, outperforming AR(1), Chronos-2, BVAR, and DFM benchmarks on FRED-MD.
Alignment pattern analysis reveals that models aligned to individual brain ROIs do not reproduce the stable cross-region alignment profiles observed across human subjects.
RISE applies CountSketch to dual lexical and semantic channels derived from output-layer gradient outer products, cutting data attribution storage by up to 112x and enabling retrospective and prospective influence analysis on LLMs up to 32B parameters.
GRASP is a scalable method for subset-level data attribution in pretraining that models interactions via a geometry-aware quadratic penalty and claims to double rank correlation while cutting costs.
citing papers explorer
-
HASTE: A Framework for Training-Free, Dynamic, and Steerable Compression of Pre-Trained Convolutional Neural Networks
HASTE enables training-free dynamic compression of pre-trained CNNs by patch-wise LSH-based merging of redundant channels, reporting 46.2% FLOPs reduction on ResNet34 CIFAR-10 with 1.25% accuracy drop.