AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems

Aniket Rege, Zinnia Nie, Mahesh Ramesh, Unmesh Raskar, Zhuoran Yu, Aditya Kusupati, Yong Jae Lee, Ramya Korlakai Vinayak

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models · 3 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
use category prompt P(c) instead of name prompt P(n) (ablation)sim(I(n),P) ITA scorer · CuRe, FLUX.1 [dev] ITA vs PSSpearman rho: 0.38 -> 0.34Hurt
use region-only prompt P(r) instead of name prompt P(n) (ablation)sim(I(n),P) ITA scorer · CuRe, FLUX.1 [dev] ITA vs PSSpearman rho: 0.38 -> 0.12Hurt
combine category and region prompts P({c,r}) in the ITA scorer (ablation)phi_ITA · CuRe, FLUX.1 [dev] ITA vs PSSpearman rho: 0.40 -> 0.42Improved
use marginal-utility ITA scorer instead of PickScorephi_ITA({c,r}) · CuRe, FLUX.1 [dev]Spearman rho vs phi*_PS: 0.34 -> 0.42Improved
use phi_PS(n) with no ground truth instead of phi_GT(n)SigLIP 2 PS scorer · CuRe, FLUX.1 [dev]Spearman rho vs phi*_PS: 0.44 -> 0.32Hurt
use divergence PS scorer on SD 1.5 instead of FLUX.1delta phi_PS({n,c}) · CuRe SigLIP 2Spearman rho vs phi*_PS: -0.31 -> 0.04Hurt
use MIA-based phi_DIV instead of LPIPS(n)diversity scorer · CuRe, FLUX.1 [dev]Spearman rho vs phi*_CuRe: -0.11 -> -0.20Improved
use phi_DIV instead of Vendi score VS(c)diversity scorer · CuRe, SD 3.5 LargeSpearman rho vs phi*_CuRe: 0.03 -> -0.22Improved
add quality weighting to Vendi score (qVS) (ablation)VS(c) · CuRe, FLUX.1 [dev]Spearman rho vs phi*_CuRe: -0.02 -> -0.02No clear effect
use SigLIP 2 instead of DINOv2 embeddings for PS benchmark scoring vs ELOphi_PS divergence · Image Arena ELOSpearman rho with ELO: 0.564 vs -0.100Mixed
use OpenAI WIT CLIP backbone for ITA scorer vs ELOphi_ITA · Image Arena ELOSpearman rho with ELO: -0.829Hurt
use Gemini 2.0 Flash judge instead of SigLIP 2 phi_GT on FLUX.1Gemini 2.0 Flash PS scorer · CuRe, FLUX.1 [dev]Spearman rho vs phi*_PS: 0.40 vs 0.44No clear effect

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