AI Paper Atlas

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

Guiding Diffusion Models with Adaptive Negative Sampling Without External Resources

Alakh Desai, Nuno Vasconcelos

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 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 adaptive negative sampling (ANSWER) to CFGSDXL · ImageNet / AE / Pick-a-Pic / DrawBench / PartiPromptswin rate (HPSv2): 41-52%Improved
add ANSWER samplingSDXL · AMT human evaluationpreference rate: 46-61% vs 8-20%Improved
add ANSWER samplingSD and SDXL · AE, Pick-a-Pic, DrawBench, PartiPromptsInception ScoreHurt
increase number of DNS steps K up to a moderate value (ablation)SDXL + ANSWER · ImageNetFID and HPSv2Improved
increase K too high (e.g. K=15) (ablation)SDXL + ANSWER · ImageNetimage quality, FID and HPSv2: K=15Hurt
add mean and variance normalization of negative noise (ablation)SDXL + ANSWER · qualitative exampleimage sharpnessImproved

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