AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

CAMP: Coherent Alignment of Multimodal Prototypes for Explainable Complementary Learning

Alvaro Lopez Pellicer, Eoin M. Kenny, Simran Lamba, Shubham Sharma, Plamen P Angelov, Saumitra Mishra

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities

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 geometry loss (ablation)Proto-Classic · Suite average (frozen encoders)score: 0.7445 -> 0.7538Improved
add allocation loss (ablation)Proto-Classic + geometry · Suite average (frozen encoders)score: 0.7538 -> 0.7658Improved
add allocation loss (ablation)Proto-Classic + geometry · Prototype healthdead prototypes: 26.6% -> 5.2%Improved
add anchor loss (ablation)Proto-Classic + geometry + allocation · Suite average (frozen encoders)score: 0.7658 -> 0.7852Improved
add class-wise OT multimodal loss (ablation)CAMP-F without OT · Suite average (frozen encoders)score: 0.7852 -> 0.8139Improved
add class-wise OT multimodal loss (ablation)CAMP-F · Cross-modal disagreementWε: 0.23 -> 0.12Improved
add all structural losses to Proto-Classic (ablation)Proto-Classic · Suite average (frozen encoders)score: 0.7445 -> 0.8139Improved
remove OT from full model (leave-one-out) (ablation)CAMP-F · Suite average (frozen encoders)score: -0.029Hurt
vary prototype capacity K (ablation)CAMP · Suite averagescore: varies by only ±0.001No clear effect
use gated fusion instead of concatenation or attention (ablation)CAMP · 16 datasetsscore: better on 15 of 16 datasetsImproved
use CAMP-F over cross-entropy MLP on same featuresfrozen Swin-L + DeBERTa-v3 · 16 benchmarksMRR: 0.174 -> 0.448Improved
end-to-end fine-tuning (CAMP-E) instead of frozen headCAMP · PTechAUC: 0.744 -> 0.800Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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