T. Tabaru

collaborators

4 papers

cs.LG2025

Direct Quantized Training of Language Models with Stochastic Rounding

Kaiyan Zhao, Tsuguchika Tabaru, Kenichi Kobayashi +3

Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weight…

nucl-ex2025

Velocity dependence of the mass modifications of $I ¨ $ and $I ¨ $ mesons in 12 GeV $p + A$ reactions

Wataru Nakai, Kazuya Aoki, Junsei Chiba +26

This study measured the invariant mass spectra of $I ¨ $ and $I ¨ $ mesons in the $e^{+} e^{-}$ decay channel for 12 GeV (12.9 GeV/ $c$ ) $p + C$ and $p + Cu$ reactions ($\sqrt{…

cs.LG2025

Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models

Istabrak Abbes, Gopeshh Subbaraj, Matthew Riemer +6

Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and…

nucl-ex2025

Analysis of spectral modification of $I ¨ $ mesons at finite density using a transport approach in the 12 GeV pA reactions

PS E325 Collaboration, Masaya Ichikawa, Philipp Gubler +26

The hadron spectrum at finite density is an important observable for exploring the origin of hadron masses. In the KEK-PS E325 experiment, the di-electron decays of phi mesons insi…

Direct Quantized Training of Language Models with Stochastic Rounding

Velocity dependence of the mass modifications of I¨ and I¨ mesons in 12 GeV p+A reactions

Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models

Analysis of spectral modification of I¨ mesons at finite density using a transport approach in the 12 GeV pA reactions

Velocity dependence of the mass modifications of $I ¨ $ and $I ¨ $ mesons in 12 GeV $p + A$ reactions

Analysis of spectral modification of $I ¨ $ mesons at finite density using a transport approach in the 12 GeV pA reactions