Orthonormal initialization for LoRA in RLVR achieves the minimal gap to full fine-tuning, stabilizes training, and outperforms standard LoRA and prior variants on mathematical reasoning benchmarks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.
citing papers explorer
-
Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR
Orthonormal initialization for LoRA in RLVR achieves the minimal gap to full fine-tuning, stabilizes training, and outperforms standard LoRA and prior variants on mathematical reasoning benchmarks.
-
Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.