2 papers
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…
cs.DS2024
Dependency-Aware Online Caching
Julien Dallot, Amirmehdi Jafari Fesharaki, Maciej Pacut +1
We consider a variant of the online caching problem where the items exhibit dependencies among each other: an item can reside in the cache only if all its dependent items are also…