They Can See It but Not Say It: Iterative Self Knowledge Re-expression in Visual Reasoning Relative Pose Identification
Source check: Source checked. Not independent scientific confirmation.
Finding: SKR-ID identifies stable VLM output biases in relative-pose reasoning and improves Macro-F1 across three open VLMs without annotations.
Technology: Self-knowledge re-expression and logit debiasing for vision-language models
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- §§5–6 use self-knowledge re-expression, logit debiasing and unannotated image pairs.
- Test and result
- §7 and Tables 2–3 report significant gains from 35.0–45.4% to 53.7–58.0% across 7-Scenes/ScanNet and ablations.
- Limitation / still unknown
- Three models, multiple scenes and three-run statistical tests support the bounded visual-reasoning result.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://arxiv.org/html/2611.10483v1
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
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.