SOURCE-LINKED INTELLIGENCE

Unifying Detection and Adaptation in Task-Free Continual Learning

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

To mitigate catastrophic forgetting in downstream continual learning (CL) for large language models (LLMs), existing methods typically constrain parameter updates or introduce task-specific adaptation modules. However, these methods often rely on explicit task boundaries during training, limiting their applicability to realistic task-free scenarios. In this paper, we propose a \textbf{Fi}sher-guided \textbf{uni}fied (\textbf{FiUni}) framework for batch-level task detection and parameter-efficient continual adaptation. FiUni is motivated by a key observation about the Fisher information matrix

Read original source ↗ Open in workspace

recordType

paper

region

Global