AI Paper Atlas

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

Libra-MIL: Multimodal Prototypes Stereoscopic Infused with Task-specific Language Priors for Few-shot Whole Slide Image Classification

Zhenfeng Zhuang, Fangyu Zhou, Liansheng Wang

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Language models for zero-shot reasoning · 2 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 instance-level language priors (ablation)Libra-MIL · TCGA-RCC 1-shotaccuracy (%): 67.0 -> 71.2Improved
add vision prototypes (ablation)Libra-MIL · TCGA-RCC 1-shotaccuracy (%): 66.0 -> 71.2Improved
use SOT fusion instead of concatenation (ablation)Libra-MIL · TCGA-RCC 1-shotaccuracy (%): 66.4 -> 71.2Improved
use SOT fusion instead of cross-attention (ablation)Libra-MIL · TCGA-RCC 4-shotaccuracy (%): 88.8 -> 91.4Improved
add bag priors in semantic aggregation (ablation)Libra-MIL · TCGA-RCC 1-shotaccuracy (%): 55.4 -> 71.2Improved
add bag priors in semantic aggregation (ablation)Libra-MIL · TCGA-RCC 4-shotaccuracy (%): 88.0 -> 91.4 ACC, 88.5 -> 88.5 F1No clear effect
add instance priors (ablation)Libra-MIL · TCGA-RCC 16-shotaccuracy (%): 92.0 -> 93.8No clear effect
use CONCH instead of Phikon/GigaPath/UNI vision encoder (ablation)Libra-MIL · TCGA-NSCLC 4-shotaccuracy (%): 72.9 -> 83.2Improved
vary number of vision prototypes Kv (ablation)Libra-MIL · TCGA-NSCLC 4-shotaccuracy (%): 83.2 at Kv=6, 79.5 at Kv=12Mixed
Libra-MIL vs best baseline (FOCUS)Libra-MIL · CAMELYON16 4-shotaccuracy (%): 61.2 -> 65.0Improved
Libra-MIL vs best baseline (CLAM MB)Libra-MIL · TCGA-NSCLC 16-shotaccuracy (%): 90.7 -> 90.8No 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