Author

Muhammed Ustaomeroglu

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence May 2026

Towards Effective Theory of LLMs: A Representation Learning Approach

The results suggest that LLM computation admits useful effective descriptions via RET: high-level, dynamically meaningful variables for interpretation, prediction, and control.

Muhammed Ustaomeroglu, Guan-Nan Qu · arXiv.org · 0 citations

#artificial intelligence Preprint Sep 2026

TRAP: Understanding and Mitigating Privacy Memorization in Language Models

TRAP, a one-sided penalty on tokenwise TRA that acts only where the target model pulls ahead of its reference, brings memorization near the level of an untrained model at little utility cost, where generic regularizers barely move and differential privacy gives up most of what fine-tuning bought.

Muhammed Ustaomeroglu, Zi-Yue Xu, Han-Shen Xiao et al. · 0 citations