arXiv (All)
open access
ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning
Low-rank adaptation (LoRA) enables parameter-efficient fine-tuning by learning low-rank weight updates. Increasing rank expands adaptation capacity, but does not guarantee that all learned directions improve downstream performance. In a diagnostic experiment with rank-16 LoRA, we show that retaining
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Beyond Low-Rank Parameterization: Narrowing the Gap Between LoRA and Full Fine-Tuning via Gradient Decomposition#1132228
- TaRA: Training-Aware Low-Rank Adaptation Initialization#924787
- TaRA: Training-Aware Low-Rank Adaptation Initialization#920553
- A Fine-Grained Analysis of the LoRA Fine-Tuning Landscape with Implications for Data Selection#1215641
- MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA Generation#1131632
Record · ID 1354389
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive