ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs
arXiv:2610.00431v1 Announce Type: new Abstract: Continual parameter-efficient fine-tuning for large language models (LLMs) must balance retention of previously acquired knowledge, adaptation to new tasks, and strict parameter budgets. We present \textbf{ChainLoRA}, a replay-free continual merging f…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-02 04:00 · arXiv stat.ML
ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs