Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning

• URL: http://arxiv.org/abs/2607.21591v1
• Date: Thu, 23 Jul 2026 17:59:46 GMT
• Title: Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning
• Abstract summary: emphProgressive Seed Pruning (PSP) scores intermediate denoised estimates and progressively narrows the set so that only promising trajectories are fully denoised.<n>PSP consistently improves reward-guided selection and achieves higher GenEval scores (automated) and better human evaluation on prompt-alignment.
• Score: 13.544618187879296
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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. \emph{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-$N$, importance-sampling, and tree-search baselines at matched compute. Project page: https://www.vision.caltech.edu/psp. Code: https://github.com/rogerioagjr/psp.

Related papers

• WARP-RM: A Warp-Augmented Relative Progress Reward Model for Data Curation [16.464426150252255]
  We present WARP (Warp-Augmented Relative Progress), a novel fully self-supervised algorithm for learning dense, signed relative progress magnitudes.<n> WARP generates per-frame progress targets via time-warp augmentations of demonstrations and we train WARP-RM to predict the normalized elapsed time between input frames.<n>We then introduce WARP-BC, which leverages these scalar reward estimates to upweight high-level action chunks during behavior cloning.
  arXiv  Detail & Related papers  (2026-06-26T17:58:06Z)
• Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement [22.349959761835468]
  Inference-time scaling has emerged as a major approach for improving reasoning capabilities.<n>We propose Iterative Partial Refinement (IPR), an inference-time scaling method for sequential diffusion.<n>IPR produces more globally consistent samples without external verification.
  arXiv  Detail & Related papers  (2026-05-19T03:53:50Z)
• Continuous Autoregressive Language Models [56.49239051750678]
  We introduce Continuous Autoregressive Language Models (CALM)<n>CALM uses a high-fidelity autoencoder to compress a chunk of K tokens into a single continuous vector.<n>We develop a comprehensive likelihood-free framework that enables robust training, evaluation, and controllable sampling.
  arXiv  Detail & Related papers  (2025-10-31T17:58:11Z)
• Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models [57.49136894315871]
  New paradigm of test-time scaling has yielded remarkable breakthroughs in reasoning models and generative vision models.<n>We propose one solution to the problem of integrating test-time scaling knowledge into a model during post-training.<n>We replace reward guided test-time noise optimization in diffusion models with a Noise Hypernetwork that modulates initial input noise.
  arXiv  Detail & Related papers  (2025-08-13T17:33:37Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models [13.312007032203857]
  Adapting a pretrained diffusion model to new objectives at inference time remains an open problem in generative modeling.<n>We introduce a tree-based approach that samples from the reward-aligned target density by propagating terminal rewards back through the diffusion chain.<n>By reusing information from previous generations, we get an anytime algorithm that turns additional compute into steadily better samples.
  arXiv  Detail & Related papers  (2025-06-25T17:59:10Z)
• Continuous Visual Autoregressive Generation via Score Maximization [69.67438563485887]
  We introduce a Continuous VAR framework that enables direct visual autoregressive generation without vector quantization.<n>Within this framework, all we need is to select a strictly proper score and set it as the training objective to optimize.
  arXiv  Detail & Related papers  (2025-05-12T17:58:14Z)
• Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding [48.55176091771745]
  Test-time scaling enhances large language model performance by allocating additional compute resources during inference.<n>Best-of-N (BoN) sampling serves as a common sampling-based scaling technique.<n>We propose Self-Truncation Best-of-N (ST-BoN), a decoding method that avoids fully generating all N samples.<n>In terms of cost, ST-BoN achieves the same performance as Full-BoN while saving computational cost by 70%-80%, and under the same cost, it can improve accuracy by 3-4 points.
  arXiv  Detail & Related papers  (2025-03-03T11:21:01Z)
• Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders [22.77397537980102]
  We show that we can compute a deterministic, model-agnostic posterior approximation (MAPA) of the true model's posterior. We present preliminary results on low-dimensional synthetic data that (1) MAPA captures the trend of the true posterior, and (2) our MAPA-based inference performs better density estimation with less computation than baselines.
  arXiv  Detail & Related papers  (2024-03-13T20:16:21Z)
• Post-Processing Temporal Action Detection [134.26292288193298]
  Temporal Action Detection (TAD) methods typically take a pre-processing step in converting an input varying-length video into a fixed-length snippet representation sequence. This pre-processing step would temporally downsample the video, reducing the inference resolution and hampering the detection performance in the original temporal resolution. We introduce a novel model-agnostic post-processing method without model redesign and retraining.
  arXiv  Detail & Related papers  (2022-11-27T19:50:37Z)
• Scaling Structured Inference with Randomization [64.18063627155128]
  We propose a family of dynamic programming (RDP) randomized for scaling structured models to tens of thousands of latent states. Our method is widely applicable to classical DP-based inference. It is also compatible with automatic differentiation so can be integrated with neural networks seamlessly.
  arXiv  Detail & Related papers  (2021-12-07T11:26:41Z)
• Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach [38.45568741734893]
  Inference in our GP model is done by a single feed forward pass through the network, significantly faster than semi-amortized methods. We show that our approach attains higher test data likelihood than the state-of-the-arts on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-02-05T13:01:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.