2 papers
cs.LG2026
FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation
Oleksii Streltsov, Oleksandra Vitko
Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by aggregating multiple samples from the completion distributio…
cs.LG2026
Recurrent Neural Networks Beyond Time: Learning from Multiple Ordered Projections
Vagan Terziyan, Artur Terziian, Oleksandra Vitko
Recurrent neural networks (RNNs) are widely used for sequence learning, yet their application is commonly associated with temporal data, although recurrent computation fundamentall…