Semantic smoothing formulates next-word distribution estimation under KL loss with embedding-based KL-proximity side information, yielding an interpolation estimator with worst-case risk O(min{Δ, d/n}) that empirically reduces perplexity on bigram models.
Attention is all you need
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Curve fitting and calculus derivative tests on a tokenization cost function identify an optimal vocabulary size that improves end-to-end ASR performance on Librispeech.
GEGLU-Transformer reconstructs EMG signals from IMU data with r=0.706 cross-subject and improves to r=0.761 after minimal adaptation under leave-one-subject-out testing.
citing papers explorer
-
Semantic Smoothing for Language Models via Distribution Estimation and Embeddings
Semantic smoothing formulates next-word distribution estimation under KL loss with embedding-based KL-proximity side information, yielding an interpolation estimator with worst-case risk O(min{Δ, d/n}) that empirically reduces perplexity on bigram models.
-
A Calculus-Based Framework for Determining Vocabulary Size in End-to-End ASR
Curve fitting and calculus derivative tests on a tokenization cost function identify an optimal vocabulary size that improves end-to-end ASR performance on Librispeech.
-
GEGLU-Transformer for IMU-to-EMG Estimation with Few-Shot Adaptation
GEGLU-Transformer reconstructs EMG signals from IMU data with r=0.706 cross-subject and improves to r=0.761 after minimal adaptation under leave-one-subject-out testing.