Separating Common and Unique Directions for Model Merging
Source check: Source checked. Not independent scientific confirmation.
Finding / tested result: The shared-basis analysis separates common and task-dominated directions in fine-tuned model updates; experiments evaluate the proposed merge method across the tested tasks and models.
Technology: CUSD model-merging method using a shared basis and dispersion scoring
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- CUSD model-merging method using a shared basis and dispersion scoring
- Limitation / still unknown
- The observed direction structure is basis- and model-dependent; broad transfer is not established.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://arxiv.org/html/2611.04108v1
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.