← Search

Mustafa Eyceoz

2 accepted papers

2026

Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning

ICLR 2026poster

Continual learning in large language models (LLMs) is prone to catastrophic forgetting, where adapting to new tasks significantly degrades performance on previously learned ones. Existing parameter-efficient methods often limit model expressivity or introduce new parameters per task, creating scalab…

Cited by 0SourcecodeScholar
2025

Hopscotch: Discovering and Skipping Redundancies in Language Models

EMNLP 2025

Modern causal language models stack many attention blocks to improve performance, but not all blocks are necessary for every task. We propose Hopscotch, a simple yet effective method that identifies and skips attention blocks with least contributions to a task and adapts to preserve output quality.

Cited by 0SourcePDFScholar