3 papers
cs.LG2026
Block-Based Double Decoders
Asher Labovich, Benjamin Bradley, Vanessa Alexander +1
Encoder-decoder models offer substantial inference-time savings over decoder-only models, but their pretraining objectives suffer from sparse supervision and dynamic sequence lengt…
cs.LG2026
Stability and Generalization in Looped Transformers
Asher Labovich
Looped transformers promise test-time compute scaling by spending more iterations on harder problems, but it remains unclear which architectural choices let them extrapolate to har…
cs.LG2025
A Case for Library-Level k-Means Binning in Histogram Gradient-Boosted Trees
Asher Labovich
Modern Gradient Boosted Decision Trees (GBDTs) accelerate split finding with histogram-based binning, which reduces complexity from to by aggregating gradients…