AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

LINA: Learning INterventions Adaptively for Physical Alignment and Counterfactual Generation in Diffusion Models

Shu Yu, Chaochao Lu

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 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 token-level intervention γ1 (ablation)Lina (SD-3.5) · PAP-OpticsSuccess rate (%): 85.1 -> 97.4Improved
add token-level intervention γ1 (ablation)Lina (SD-3.5) · WinogroundSuccess rate (%): 60.2 -> 79.5Improved
add latent-level contrastive guidance γ2 (ablation)Lina (SD-3.5) · PAP-OpticsSuccess rate (%): 81.3 -> 97.4Improved
add latent-level contrastive guidance γ2 (ablation)Lina (SD-3.5) · PAP-DensitySuccess rate (%): 78.0 -> 92.3Improved
add adaptive intervention module instead of fixed γ (ablation)Lina (SD-3.5) · WinogroundSuccess rate (%): 68.4 -> 79.5Improved
add adaptive intervention module instead of fixed γ (ablation)Lina (SD-3.5) · PAP-DensitySuccess rate (%): 85.2 -> 92.3Improved
use reallocated causality-aware schedule instead of standard (ablation)Lina (SD-3.5) · PAP-OpticsSuccess rate (%): 92.3 -> 97.4Improved
use reallocated causality-aware schedule instead of standard (ablation)Lina (SD-3.5) · WinogroundSuccess rate (%): 74.3 -> 79.5Improved
apply Lina to SD-3.5-largeSD-3.5-large · PAP-DensitySuccess rate (%): 54.2 -> 92.3Improved
apply Lina to FLUX.1FLUX.1-Krea-dev · WinogroundSuccess rate (%): 65.5 -> 83.0Improved
add LoRA finetuning to SD-3.5SD-3.5-large · WinogroundSuccess rate (%): 54.4 -> 57.3No clear effect
add PPAD to SD-3.5SD-3.5-large · WinogroundSuccess rate (%): 54.4 -> 62.6No 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