AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Learning by Analogy: A Causal Framework for Compositional Generalization

Lingjing Kong, Shaoan Xie, Yang Jiao, Yetian Chen, Yanhui Guo, Simone Shao, Yan Gao, Guangyi Chen, Kun Zhang

CVPR 2026 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability

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 time-dependent (hierarchical) conditioning (ablation)HierDiff · DPG-BenchRelation: 86.29 -> 87.14Improved
add time-dependent (hierarchical) conditioning (ablation)HierDiff · DPG-BenchOther: 85.64 -> 87.77Improved
add sparsity regularization on attention overlap (ablation)HierDiff · DPG-BenchGlobal: 83.09 -> 85.77Improved
add sparsity regularization on attention overlap (ablation)HierDiff · DPG-BenchEntity/Relation: Entity 86.44 -> 85.15; Relation 87.14 -> 86.82Mixed
HierDiff vs ELLA with hierarchical injection and sparsitySD v1.5 · DPG-Benchoverall score: 74.91 -> 79.28Improved
scale HierDiff to 4.8B diffusion transformerHierDiff-DiT · DPG-Bench (large-scale DiT)DPG: 84.9 vs FLUX-schnell 84.8No 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