2 papers
cs.LG2026
Critical Windows of Complexity Control: When Transformers Decide to Reason or Memorize
Sarwan Ali
Recent work has shown that Transformers' compositional generalization is governed by \emph{complexity control}, initialization scale and weight decay, which steers training toward…
cs.LG2025
Explicit Path CGR: Maintaining Sequence Fidelity in Geometric Representations
Sarwan Ali
We present a novel information-preserving Chaos Game Representation (CGR) method, also called Reverse-CGR (R-CGR), for biological sequence analysis that addresses the fundamental l…