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...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Jaesung Jun, Youngmin Ro
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	IEEE 2026-01-01
Σειρά:	IEEE Access
Θέματα:	Low-rank adaptation parameter-efficient fine-tuning large language models group-wise decomposition effective rank transformer fine-tuning
Διαθέσιμο Online:	https://ieeexplore.ieee.org/document/11424420/
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!