CSD2 min read
CSD: Common-Support Distillation for Cross-Tokenizer Knowledge Transfer
Cross-tokenizer logits distillation enables knowledge transfer across model families, allowing students to learn from stronger or more specialized teachers. However, differences in vocabulary and segmentation make teacher and student next-token distributions difficult to align.
By Mingyu Yang, Sharath Turuvekere Sreenivas, Adithyakrishna Venkatesh Hanasoge, Nima Tajbakhsh, Ashwath Aithal, Pavlo MolchanovarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Oct 22, 2026.
Comments
Sign in to join the discussion.