AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Zero-Shot Rankability: Revealing Latent Ordinal Structure in Multimodal Large Language Models via Language

Nam Hyeon-Woo, Moon Ye-Bin, Sohwi Lim, Kwon Byung-Ki, Tae-Hyun Oh

ICML 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs

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 attribute-specific conditional prompt to the image embedding (ablation)Qwen2.5-VL-7B text-driven rank axis · Average over 8 datasetsSRCC: 0.544 -> 0.734Improved
add attribute-specific conditional prompt (ablation)Qwen3-VL-8B text-driven rank axis · Average over 8 datasetsSRCC: 0.558 -> 0.710Improved
add attribute-specific conditional prompt (ablation)Qwen3-VL-4B text-driven rank axis · Average over 8 datasetsSRCC: 0.587 -> 0.743Improved
add attribute-specific conditional prompt (ablation)Qwen3-VL-2B text-driven rank axis · Average over 8 datasetsSRCC: 0.544 -> 0.724Improved
add conditional prompt (abstract aesthetics) (ablation)Qwen2.5-VL-7B text-driven rank axis · KonIQ-10kSRCC: 0.349 -> 0.763Improved
add conditional prompt (recency) (ablation)Qwen2.5-VL-7B text-driven rank axis · HCISRCC: 0.234 -> 0.571Improved
add conditional prompt to the supervised linear probe embedding (ablation)Qwen2.5-VL-7B linear probing · Average over 8 datasetsSRCC: 0.799 -> 0.839Improved
apply I0T modality gap-reduction to frozen CLIP-RN50CLIP-RN50 zero-shot rank axis · KonIQ-10kSRCC: 0.466 -> 0.661Improved
apply I0T modality gap-reduction to frozen CLIP-ViTB/32CLIP-ViTB/32 zero-shot rank axis · KonIQ-10kSRCC: 0.502 -> 0.663Improved
apply I0T modality gap-reduction to frozen CLIP-CNXCLIP-CNX zero-shot rank axis · KonIQ-10kSRCC: 0.508 -> 0.738Improved
replace cross-attention MLLM (IDEFICS1) with projector-based (IDEFICS2)IDEFICS zero-shot rank axis · KonIQ-10kSRCC: 0.338 -> 0.718Improved
replace cross-attention MLLM (IDEFICS1) with projector-based (IDEFICS2)IDEFICS zero-shot rank axis · UTKFaceSRCC: 0.774 vs. 0.751No clear effect

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