一作NeurIPS 2026Poster· Deep Learning / Algorithms
ByteDistill: Cross-Tokenizer Distillation via Chunk-wise Byte-Level Distribution Alignment
Yang Chen · Xianqi Yu · Shaowei Yao (Taobao & · Fuyu Lv · Chenhe Dong (Taobao & · Xingxian Liu (Taobao &