AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Learning Robust Intervention Representations with Delta Embeddings

Panagiotis Alimisis, Christos Diou

ICLR 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
use delta embeddings with CDE losses instead of vanilla classifierViT-DINO · Causal Triplet single-object ProcTHOR (OOD systematic)accuracy: 0.47 -> 0.75Improved
add supervised contrastive loss (ablation)CDE ViT-DINO · Causal Triplet single-object ProcTHOR (OOD systematic)accuracy: 0.68 -> 0.75Improved
add sparsity loss (ablation)CDE ViT-DINO · Causal Triplet single-object ProcTHOR (OOD systematic)accuracy: 0.73 -> 0.75Improved
add contrastive and sparsity losses to delta embedding trained with CE (ablation)CDE ViT-DINO · Causal Triplet single-object ProcTHOR (OOD systematic)accuracy: 0.67 -> 0.75Improved
use delta embedding with CE only vs vanilla baseline (ablation)ViT-DINO · Causal Triplet single-object ProcTHOR (OOD systematic)accuracy: 0.47 -> 0.67Improved
use patch-wise Top-K model with larger k (ablation)patch-wise CDE · multi-object ProcTHOR (smaller subset)OOD accuracy: 0.42 -> 0.48Improved
increase k on real-world scenes (ablation)patch-wise CDE · Epic-Kitchens (smaller subset)OOD accuracy: 0.12 -> 0.15Improved
larger alpha_contrast than alpha_sparsity (ablation)CDE · Causal Triplet single-object ProcTHOR (OOD systematic, smaller subset)accuracy: 0.31 -> 0.33Improved
use CDE with ResNet-18 backbone (ablation)CDE · single-object systematic (smaller subset)accuracy: 0.54 -> 0.45Hurt
use ViT-MAE vs ViT-DINO backbone on multi-objectpatch-wise CDE · Causal Triplet multi-object ProcTHOR (systematic shift)OOD accuracy: 0.45 -> 0.30Hurt
CDE vs oracle-mask baselinepatch-wise CDE ViT-CLIP · Causal Triplet multi-object ProcTHOR (systematic shift)OOD accuracy: 0.42 -> 0.48Improved
CDE vs best baseline on real-world Epic-Kitchenspatch-wise CDE ViT-CLIP · Causal Triplet Epic-Kitchens (systematic shift)OOD accuracy: 0.27 -> 0.34Improved

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