Hardmax transformers converge to leader-determined clusters, enabling an interpretable model for sentiment analysis.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
SNLP achieves up to 2.58x wall-clock speedup on 0.5B Transformers via architecture-specific Newton corrections (IDN/HCN) that enable layer-parallel inference while preserving perplexity in milder settings.
citing papers explorer
-
SNLP: Layer-Parallel Inference via Structured Newton Corrections
SNLP achieves up to 2.58x wall-clock speedup on 0.5B Transformers via architecture-specific Newton corrections (IDN/HCN) that enable layer-parallel inference while preserving perplexity in milder settings.