cs.CVNov 18, 2026

ProxySearch: Decoupled Inference-Time Scaling for Diffusion Models via Asymmetric Noise-Rank Transfer

Authors: Seungwook Kim, Jongmin Lee

Organizations: GenGenAI · Chung-Ang University

Abstract

Noise search at inference time improves text-to-image diffusion but requires many multi-step teacher rollouts per query. Distilled few-step models are now routinely released, yet their potential as proxies inside noise search is uncharacterized. We measure proxy-teacher rank agreement across three distillation regimes and three backbones (DiT, MMDiT, UNet) and find a sharp asymmetry. On our main pool, closed-form image statistics transfer from the proxy to the teacher (Spearman ρρ up to 0.80), while learned semantic scorers do not (ρ≤ρ\le 0.12). Paired null controls trace this rank to the first denoising step for coarse statistics and to distillation for finer ones. We use the asymmetry for noise search under a joint constraint: a semantic reward specifies content, and a numeric target specifies image statistics. In PROXYSEARCH, the proxy filters candidates by statistical match in 1 step, and the teacher returns the survivor with the highest semantic reward. No weight trades one objective against the other. On FLUX-1024, PROXYSEARCH tightens the statistical target by 21-23% at the same number of teacher trajectories, with no detected loss on the optimized reward.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jul 3, 2026

A Decomposable Probe for Few-Step Diffusion Models: Prompt, Latent, and Score Selectivity across Backbone Families and Distillation Paradigms

Few-step distilled diffusion students cut text-to-image inference from ~50 to 1-8 network evaluations, but the quality gap is usually summarised by a single FID/CLIP scalar that cannot say which axis of the conditioning response changed, nor whether a behaviour comes from the architecture, the distillation objective, or simply from being a diffusion model. We replace the scalar with a decomposable probe that injects controlled perturbations along three layers (prompt encoder, denoiser input, denoiser output) under three modes (mean, variance, scale) and six strengths, reporting a bootstrap-median Bures W2^2 selectivity ratio on Inception features. Under a single matched estimator across 23 models -- five teachers and 18 distilled students spanning five backbone families (SDXL, SD1.5, SD3.5, PixArt-alpha, FLUX), three architecture classes (UNet, DiT, MMDiT), and five distillation paradigms -- the three layers read three empirically separable factors: the prompt layer is a universal prompt-mean response (a sanity channel, not a discriminator), the latent layer reads the prediction type, and the score layer reads the distillation objective. Our main result: within this sweep, the latent layer is a near-binary detector of rectified-flow backbones. Its ratio exceeds 1 across a sustained low-to-mid band only for rectified-flow models (SD3.5, FLUX); no epsilon-prediction model qualifies. A matched epsilon-prediction control (PixArt-alpha) rules out wide-T5 conditioning, and the fingerprint survives adversarial (ADD) distillation as both teacher and student. Two secondary score-layer findings hold under narrower scopes: a canonical 4-step ADD-vs-rest contrast on the UNet families with a non-ADD baseline, and a CI-separated trajectory-rollout early-strength score spike on both UNet and DiT. All ratios are CI-citable under one estimator; we release the per-cell tables and the estimator.
Nov 19, 2026

Keystone: Judging Previews at Key Steps for Test-Time Search in Diffusion Models

Text-to-image diffusion and flow models yield a preview, their clean-image estimate, at every denoising step. When they miscount, drop or misplace objects, test-time search is in a bind: its verifiers are reward models built for finished images, so judging early misreads blurry previews, and judging late, as best-of-N does, pays to fully denoise doomed candidates. We find that the image is not the problem: the outcome is settled as denoising starts, by the seed or by a stochastic sampler's first steps, and already shows in early previews; what fails on them is the judge, as reward models read them near chance on several kinds of prompts. We introduce Keystone, a training-free judge of previews that compiles a prompt into typed questions about its objects, counts, colours and positions and has an off-the-shelf multimodal decision model answer them. Asked this way, the judge reads counts and positions from early previews better than reward models read them from finished images. Searching at these key steps on GenEval with SD3.5-Medium, Keystone's adaptive search and pruning significantly outperform best-of-8 with every other verifier at under half its generator compute, and as a drop-in verifier there, the Keystone score significantly improves best-of-N, progressive seed pruning and FK steering; without retuning, both searches stay significantly above the strongest other verifier's best-of-N on average over four base models and three benchmarks. Keystone thus moves test-time judgment to the key steps where the outcome already shows.
Jul 23, 2026

Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning

Diffusion and flow-matching models dominate conditional image generation, yet inference-time scaling for these models is far less developed than for autoregressive language models. Because final quality is highly sensitive to the initial noise seed, many approaches spend extra compute on seed search or resampling under a black-box reward, but typically maintaining a constant memory footprint throughout inference. We show that relaxing this constraint enables an underexplored inference-time scaling axis: by front-loading exploration, evaluating many seeds early, and pruning aggressively, we can use a fixed compute budget more effectively. Progressive Seed Pruning (\PSP) scores intermediate denoised estimates and progressively narrows the candidate set so that only promising trajectories are fully denoised, while keeping the total number of model evaluations fixed. Across diffusion and flow-matching backbones, \PSP \ consistently improves reward-guided selection and achieves higher GenEval scores (automated) and better human evaluation on prompt-alignment than best-of-NN, importance-sampling, and tree-search baselines at matched compute. Project page: https://www.vision.caltech.edu/psp. Code: https://github.com/rogerioagjr/psp.