AI Paper Atlas

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

Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation

Dahee Kwon, Haeun Lee, Jaesik Choi

ICML 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 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
apply DAVE DC attenuation in early denoising stepsSD3.5 · ImageNetVendi: 1.71 -> 2.33Improved
apply DAVE DC attenuation in early denoising stepsSD3.5 · MS-COCOFID: 36.38 -> 29.56Improved
apply DAVE in the in-batch setting versus SPELL, DiverseFlow, Oscar, PGSD3.5 · MS-COCO in-batchRecall: 0.255 -> 0.441Improved
sample intervention block randomly from pool L instead of one fixed block (ablation)DAVE · ImageNetVendi: 2.33 -> 2.50 (SD3.5)Improved
lengthen the intervention window (larger temporal cutoff tau) (ablation)DAVE · SD3structural variation vs image qualityMixed
lower attenuation strength alpha (ablation)DAVE · SD3LPIPSMixed
amplify DC component (alpha > 1) (ablation)DAVE · SD3structural changeNo clear effect
calibrate block pool L on a different dataset (ablation)DAVE · SD3.5 MS-COCO/ImageNetVendi: 2.0275 -> 1.8840No clear effect
apply DAVE on a distilled modelSD3.5-Large-Turbo · Distilled samplingVendi: 1.383 -> 1.643Improved
combine DAVE with higher CFG scalesSD3 · CFG 7Vendi: 3.385 -> 3.828Improved
apply DAVE at CFG 3SD3 · CFG 3Vendi: 2.540 -> 2.307Hurt
apply DAVE to complex promptsSD3 · PartiPromptsVendi: 1.511 -> 2.006 (Comp.)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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