AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling

Gongye Liu, Bo Yang, Zhi Yida, Zhizhou Zhong, Lei Ke, Didan Deng, Han Gao, Yongxiang Huang, Kaihao Zhang, Hongbo Fu, Wenhan Luo

ICML 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
add multi-noise test-time ensembling (ablation)DiNa-LRM · Average (4 sets)pairwise preference accuracy (%): 71.49 -> 72.48Improved
use noise-calibrated variance instead of fixed variance (ablation)DiNa-LRM · HPDv2pairwise preference accuracy (%): 78.72 -> 82.13Improved
use noise-calibrated variance with ensembling (ablation)DiNa-LRM* · Average (4 sets)pairwise preference accuracy (%): 70.41 -> 72.48Improved
train with uniform timestep sampling instead of constant t=0 (ablation)DiNa-LRM · Average (4 sets)pairwise preference accuracy (%): 64.93 -> 70.68Improved
train with uniform timestep sampling instead of LogitNormal(0.8,1.0) (ablation)DiNa-LRM · Average (4 sets)pairwise preference accuracy (%): 70.58 -> 71.49Improved
LoRA fine-tune backbone instead of freezing (ablation)DiNa-LRM · Average (4 sets)pairwise preference accuracy (%): 70.27 -> 71.49Improved
use gated Q-Former head instead of average pooling (ablation)DiNa-LRM · Average (4 sets)pairwise preference accuracy (%): 71.03 -> 71.49Improved
use gated Q-Former head instead of transformer plus average pooling (ablation)DiNa-LRM · Average (4 sets)pairwise preference accuracy (%): 71.14 -> 71.49Improved
increase feature layers from 8 to 12 (ablation)DiNa-LRM · Average (4 sets)pairwise preference accuracy (%): 68.07 -> 71.49Improved
increase feature layers from 12 to 20 (ablation)DiNa-LRM · Average (4 sets)pairwise preference accuracy (%): 71.49 -> 72.76Improved
add multi-noise ensembling to fixed-variance model (ablation)DiNa-LRM (Fixed variance) · Average (4 sets)pairwise preference accuracy (%): 70.68 -> 70.41Hurt
scale diffusion backbone from SD3.5-M (2B) to FLUX.1-Dev (12B)DiNa-LRM · Average (4 sets)pairwise preference accuracy (%): 71.49 -> 69.87No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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