Papers with full-precision fine-tuning
Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for quantized fine-tuning fail to address activation outliers . existing methods incur high computational/memory costs or fail to adequately address outlier activation . |
| Approach: | They propose a Quantized parameter-efficient fine-tuning framework that suppresses outliers exclusively in invariant channels using lightweight operations. |
| Outcome: | The proposed framework reduces outliers in invariant channels while reducing quantization errors. |