LoRMA: Low-Rank Multiplicative Adaptation for LLMsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
DeLoRA: Decoupling Angles and Strength in Low-rank AdaptationInternational Conference on Learning Representations (ICLR), 2025 |
RandLoRA: Full-rank parameter-efficient fine-tuning of large modelsInternational Conference on Learning Representations (ICLR), 2025 |