GroupLoRA: Enhancing Rank Effectiveness Through Group-Wise Decomposition for Low-Rank Adaptation

The rapid advancement of Large Language Models (LLMs) and Large Vision Models (LVMs) has achieved breakthrough performance but has also created significant deployment challenges due to their massive scale, often exceeding 100 billion parameters. Parameter-Efficient Fine-tuning (PEFT) methods, partic...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Jaesung Jun, Youngmin Ro
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IEEE 2026-01-01
Edice:	IEEE Access
Témata:	Low-rank adaptation parameter-efficient fine-tuning large language models group-wise decomposition effective rank transformer fine-tuning
On-line přístup:	https://ieeexplore.ieee.org/document/11424420/
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!