Preprints|Short CommunicationNot peer reviewedSpeculative Decoding Under Memory ConstraintsRahul Desai, Yuki SaitoVersion 1 · 5 November 2026 · 10.xxxx/ctm.pp.2026.0009Abstract PDF 437 1210 cited
Proceedings|Full paperBest paperMixed-Precision Distillation for 4-bit Phone-Class ModelsYuki Saito, Daniel OkaforSEODML 2026 · pp. 1–10 · 1 October 2026 · 10.xxxx/ctm.pr.2026.0006Abstract PDF 980 3601 cited
Proceedings|Short paperProfiling Energy Use of Small Language Models on Mobile SoCsYuki Saito, Mei TanakaSEODML 2026 · pp. 21–26 · 1 October 2026 · 10.xxxx/ctm.pr.2026.0008Abstract PDF 520 1750 cited
Research Archive|ModelDistilled 4-bit Assistant CheckpointsYuki Saito, Daniel OkaforVersion 1.0 · CC BY 4.0 · 12 September 2026 · 10.xxxx/ctm.ar.2026.0008View record 840 3720 cited
Publishing|Research ArticleUnder peer reviewQuantisation-Aware Distillation for On-Device AssistantsDaniel Okafor, Yuki Saito, Priya VenkataramanVersion 1 · 1 reviewer report · 28 August 2026 · 10.xxxx/ctm.pb.2026.0006Abstract PDF 2,144 7862 cited