Pith. sign in

REVIEW 6 cited by

Test-Time Scaling of Diffusion Models via Noise Trajectory Search

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.03164 v2 pith:SMGVAPLP submitted 2025-05-24 cs.LG

Test-Time Scaling of Diffusion Models via Noise Trajectory Search

classification cs.LG
keywords noisediffusionsearchdenoisingscalingtest-timetrajectoryduring
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The iterative and stochastic nature of diffusion models enables test-time scaling, whereby spending additional compute during denoising generates higher-fidelity samples. Increasing the number of denoising steps is the primary scaling axis, but this yields quickly diminishing returns. Instead optimizing the noise trajectory--the sequence of injected noise vectors--is promising, as the specific noise realizations critically affect sample quality; but this is challenging due to a high-dimensional search space, complex noise-outcome interactions, and costly trajectory evaluations. We address this by first casting diffusion as a Markov Decision Process (MDP) with a terminal reward, showing tree-search methods such as Monte Carlo tree search (MCTS) to be meaningful but impractical. To balance performance and efficiency, we then resort to a relaxation of MDP, where we view denoising as a sequence of independent contextual bandits. This allows us to introduce an $\epsilon$-greedy search algorithm that globally explores at extreme timesteps and locally exploits during the intermediate steps where de-mixing occurs. Experiments on EDM and Stable Diffusion reveal state-of-the-art scores for class-conditioned/text-to-image generation, exceeding baselines by up to $164\%$ and matching/exceeding MCTS performance. To our knowledge, this is the first practical method for test-time noise trajectory optimization of arbitrary (non-differentiable) rewards.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion

    cs.LG 2026-05 unverdicted novelty 7.0

    CDM amortizes SMC inference for reward-tilted discrete diffusion by training a parameterized twist function on contrastive samples with closed-form kernels.

  2. NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment

    cs.LG 2026-06 unverdicted novelty 6.0

    NTRK uses a whitening operator to tilt the noise term in diffusion reverse kernels for reward guidance, outperforming baselines with 20x fewer steps on aesthetic tasks.

  3. NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment

    cs.LG 2026-06 unverdicted novelty 6.0

    NTRK is a reward-guided diffusion sampler that uses a whitening operator to bias the noise term toward high-reward outcomes, outperforming baselines with up to 20x fewer sampling steps on aesthetic tasks.

  4. Stream-T1: Test-Time Scaling for Streaming Video Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    Stream-T1 is a test-time scaling framework for streaming video generation using scaled noise propagation from history, reward pruning across short and long windows, and feedback-guided memory sinking to improve tempor...

  5. On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization

    cs.LG 2026-07 conditional novelty 5.5

    Online fine-tuning of discrete diffusion models with complementary acquisition, CVaR shaping, density-entropy debiasing, replay, and validity control finds better molecules under fixed oracle budgets than offline fine...

  6. Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning

    cs.CV 2026-06 unverdicted novelty 5.0

    A survey of test-time scaling for multimodal foundation models that introduces a three-way taxonomy of sampling, feedback, and search approaches along with applications and benchmarks.