AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Context-Conditioned Predicate Semantics via Prototype Feedback

NamGyu Jung, Chang Choi

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 0 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 edge update to PE-Net (ablation)PE-Net · VG-150 PredClsmR@100: +2.3Improved
add edge update to PE-Net (ablation)PE-Net · VG-150 SGDetmR@100: +0.6Improved
add concatenation-based prototype alignment to edge-only variant (ablation)AlignG · VG-150 SGClsmR@100: +2.2Improved
replace concatenation prototype update with GRU (ablation)AlignG · VG-150 PredClsmR@100: +1.2Improved
replace concatenation prototype update with GRU (ablation)AlignG · VG-150 SGClsmR@100: +0.4Improved
replace concatenation prototype update with GRU (ablation)AlignG · VG-150 SGDetmR@100: +0.5Improved
use GRU update instead of EMA (ablation)AlignG · VG-150 PredClsF@100: 43.75 -> 47.47Improved
use GRU update instead of identity (no update) (ablation)AlignG · VG-150 PredClsR@100: 69.06 -> 65.06Hurt
add similarity penalty (ablation)AlignG · VG-150 PredClsF@100: 41.5 -> 47.5Improved
add diversity constraint (ablation)AlignG · VG-150 PredClsF@100: 38.6 -> 47.5Improved
add alignment loss (ablation)AlignG · VG-150 PredClsF@100: 42.7 -> 47.5Improved
double all loss weights (ablation)AlignG · VG-150 PredClsF@100: 47.5 -> 38.7Hurt

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