AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment

Jisung Hwang, Yunhong Min, Jaihoon Kim, I-Chao Shen, Minhyuk Sung

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 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
NoiseTilt (25 NFE) instead of SVDD (500 NFE)FLUX · Aesthetic image generation (target Aesthetic Score)Aesthetic Score: 7.1363 -> 7.4510Improved
add Best-of-N to NoiseTilt (500 NFE) (ablation)NoiseTilt · Aesthetic image generation (target Aesthetic Score)Aesthetic Score: 7.4510 -> 7.9656Improved
add Best-of-N to NoiseTilt (500 NFE) (ablation)NoiseTilt · Aesthetic image generation (target Aesthetic Score)ImageReward: 1.2565 -> 1.1669Hurt
add Best-of-N to NoiseTilt (500 NFE) (ablation)NoiseTilt · Text-aligned image generation (target PickScore)PickScore: 0.2224 -> 0.2327Improved
add Best-of-N to NoiseTilt (500 NFE) (ablation)NoiseTilt · Text-aligned image generation (target PickScore)VQA Score: 0.8210 -> 0.8017Hurt
NoiseTilt (25 NFE) instead of SVDD (500 NFE)FLUX · Text-aligned image generation (target PickScore)PickScore: 0.2204 -> 0.2224Improved
NoiseTilt instead of DPSWan2.1 · Preference-aligned video generation (VBench)VideoReward: -0.130 -> 3.465Improved
NoiseTilt instead of BaseWan2.1 · Preference-aligned video generation (VBench)VideoReward: -0.399 -> 3.465Improved
NoiseTilt instead of FreeDoMWan2.1 · Preference-aligned video generation (VBench)Dynamic Degree: 0.6900 -> 0.9500Improved
DPS guidance instead of BaseWan2.1 · Preference-aligned video generation (VBench)Aesthetic Quality: 0.6104 -> 0.5867Hurt
add MixGRPO fine-tuningFLUX · Text-aligned image generation with fine-tuned modelPickScore: 0.2054 -> 0.2166Improved
add NoiseTilt on top of MixGRPO instead of DPSMixGRPO · Text-aligned image generation with fine-tuned modelPickScore: 0.2235 -> 0.2545Improved

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