AI Paper Atlas

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

Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthiness

Xiang Fang, Wanlong Fang, Wei Ji

ICML 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 0 citations (OpenAlex)

Read the paper

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 Immuno-VLM semantic antibody training to frozen CLIPCLIP ViT-B/16 · ImageNet-O (Near-OOD)AUROC: 66.8 -> 83.4Improved
add Immuno-VLM to MCM-style zero-shot baselineCLIP ViT-B/16 · ImageNet-O (Near-OOD)FPR95: 61.3 -> 28.5Improved
add Immuno-VLM adapter to frozen CLIPCLIP ViT-B/16 · ImageNet-1K IDaccuracy: 78.2 -> 78.5No clear effect
train CSI-style objective instead of keeping zero-shotCLIP ViT-B/16 · ImageNet-1K IDaccuracy: 78.2 -> 76.5Hurt
add Gaussian-noise adapter negatives (ablation)Frozen CLIP · ImageNet-O (Near-OOD)AUROC: 66.8 -> 68.2 (+1.4)Improved
use random dictionary words as negatives (ablation)Frozen CLIP · ImageNet-O (Near-OOD)AUROC: 66.8 -> 72.5 (+5.7)Improved
use LLM-generated antibodies without filter (ablation)Frozen CLIP · ImageNet-O (Near-OOD)AUROC: 66.8 -> 79.8 (+13.0)Improved
add semantic filter and EVT thresholding to LLM antibodies (ablation)Immuno-VLM · ImageNet-O (Near-OOD)AUROC: 79.8 -> 83.4Improved
add semantic filter and EVT thresholding to LLM antibodies (ablation)Immuno-VLM · ImageNet-1K IDaccuracy: 77.6 -> 78.5Improved
set margin m to 0.0 instead of 0.2 (ablation)Immuno-VLM · OOD detectionAUROC: 76.2Hurt
raise margin m to 0.5 or above (ablation)Immuno-VLM · ImageNet-1K IDaccuracy: -4.2%Hurt
remove the upper similarity bound of the antibody filter (ablation)Immuno-VLM · ImageNet-1K IDaccuracy: -12%Hurt

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