2 papers
cs.IT2026
Compression with Privacy-Preserving Random Access
Venkat Chandar, Aslan Tchamkerten, Shashank Vatedka
We show that an i.i.d.\ binary source sequence can be losslessly compressed at any rate above entropy while ensuring that the decoding of any reveals no info…
cs.LG2026
Effective Context in Transformers: An Analysis of Fragmentation and Tokenization
Amirmehdi Jafari Fesharaki, Mohammadamin Rami, Aslan Tchamkerten
Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representations may be lossless. Yet, unde…