AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Training-Free Personalization via Retrieval and Reasoning on Fingerprints

Deepayan Das, Davide Talon, Yiming Wang, Massimiliano Mancini, Elisa Ricci

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add fingerprint attributes to CoT reasoning (ablation)R2P (CoT, no pairwise) · PerVAcaptioning recall: 62.8 -> 71.2Improved
add fingerprint attributes to CoT reasoning (ablation)R2P (CoT, no pairwise) · PerVAweighted recognition: 84.7 -> 91.8Improved
add CoT reasoning alone, without fingerprint attributes (ablation)R2P naive prompting · PerVAweighted recognition: 86.5 -> 84.7Hurt
add pairwise reasoning on top of CoT and fingerprints (ablation)R2P · PerVAcaptioning recall: 71.2 -> 72.5Improved
add pairwise reasoning only (ablation)R2P naive prompting · PerVAweighted recognition: 86.5 -> 92.3Improved
add CoT to pairwise reasoning without attributes (ablation)R2P · PerVArecognition and captioning: 92.3 -> 91.6 Wtd, 65.9 -> 67.3 recallMixed
use human-specified attributes instead of VLM fingerprints (ablation)R2P · PerVAcaptioning recall: 72.5 -> 72.8No clear effect
use attribute verification instead of abstention (ablation)R2P · PerVAcaptioning recall: 70.7 -> 72.5Improved
use attribute verification instead of logits-based check (ablation)R2P · PerVAcaptioning recall: 70.9 -> 72.5Improved
use attribute verification instead of always running pairwise reasoning (ablation)R2P · PerVAcaptioning recall: 72.3 -> 72.5No clear effect
use attribute verification instead of no estimation (ablation)R2P · Yo'LLaVAcaptioning recall: 82.0 -> 91.5Improved
use fused image-text retrieval instead of CLIP image only (ablation)R2P · PerVAHIT@3: 76.9 -> 87.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy