Constella

Constella rides along in every tab, reading the page beside you, writing with you in your docs, and getting smarter with everything you save. One sidekick for the whole web.

Parameter-efficient finetuning methods based on spectral decomposition have enabled progress in continual learning. Large Language Models (LLMs) have achieved remarkable performance across diverse reasoning and generation tasks (Zhao et al., 2023; Minaee et al., 2024) . Among PEFT approaches, Low-Rank Adaptation (LoRA) (Hu et al., 2021) has emerged as one of the most widely adopted.