LLM News

Every LLM release, update, and milestone.

Filtered by:parameter-efficient-tuning✕ clear
research

Spectral Surgery: Training-Free Method Improves LoRA Adapters Without Retraining

Researchers propose Spectral Surgery, a training-free refinement method that improves Low-Rank Adaptation (LoRA) adapters by decomposing trained weights via SVD and selectively reweighting singular values based on gradient-estimated component sensitivity. The approach achieves consistent gains across Llama-3.1-8B and Qwen3-8B—up to +4.4 points on CommonsenseQA and +2.4 pass@1 on HumanEval—by adjusting only ~1,000 scalar coefficients.