Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training

• URL: http://arxiv.org/abs/2608.06125v1
• Date: Thu, 06 Aug 2026 14:55:42 GMT
• Title: Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training
• Abstract summary: We propose textscSURE, a unified latent-space framework for image and video diffusion models.<n>It learns reward distributions and directly uses their reliability to guide dense post-training.<n>textscSURE-REFL achieves the highest VBench quality, semantic, and total scores among the evaluated methods.
• Score: 51.18425726646089
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Latent reward models can supervise visual diffusion models without decoding intermediate states into pixel space. This makes alignment with human preferences more efficient. However, existing latent reward models output only scalar scores. They do not estimate the uncertainty of each prediction. The generator therefore cannot determine which feedback is reliable. This can drive optimization in the wrong direction and lead to reward hacking. We propose \textsc{SURE}, a unified latent-space framework for image and video diffusion models. It learns reward distributions and directly uses their reliability to guide dense post-training. First, we propose sample-adaptive latent reward model (\textsc{SURE-LRM}). It predicts a Gaussian utility for each noisy latent. Its mean predicts the reward score. Its variance reflect the uncertainty of prediction without human annotation. The learned distribution then guides post-training through uncertainty-guided reward feedback learning (\textsc{SURE-REFL}). This method provides uncertainty-guided dense feedback along the denoising trajectory. At selected transitions, \textsc{SURE-REFL} queries the frozen \textsc{SURE-LRM}. It converts detached variance into reliability weights for samples at the same transition. Each weighted reward is backpropagated only through its local transition. The entire process remains in latent space and requires neither pixel-space decoding nor the full denoising graph. Experiments show that \textsc{SURE-LRM} improves preference prediction over strong baselines. \textsc{SURE-REFL} achieves the sota performance among various metrics and further improves optimization stability. It also achieves the highest VBench quality, semantic, and total scores among the evaluated methods.

Related papers

• Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias [11.400279490725042]
  Probabilistic downscaling is a central challenge to atmospheric science, climate modeling, and other multiscale physical systems.<n>A widely used paradigm decomposes the problem into a deterministic mean predictor followed by a residual generator.<n>We show that the root cause is residual target miscalibration, the residual distribution induced during training differs systematically from the one required at test time due to downscaling bias.
  arXiv  Detail & Related papers  (2026-06-29T18:47:34Z)
• MARBLE: Multi-Aspect Reward Balance for Diffusion RL [71.6241143519038]
  Reinforcement learning has become the dominant approach for aligning diffusion models with human preferences.<n>Existing practice deal with multiple rewards by training one specialist model per reward.<n>We propose MARBLE, a gradient-space optimization framework that maintains independent advantage estimators for each reward.
  arXiv  Detail & Related papers  (2026-05-07T16:20:42Z)
• Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking [0.20305676256390937]
  This paper decomposes uncertainty into its sources, distinguishes variance that shrinks with more data, and uses design-study projections to reduce total error.<n>Applying the approach to ideology annotation, safety classification, MMLU benchmarking, and a human-validated propaganda audit reveals different dominant variance sources by domain and scoring method.
  arXiv  Detail & Related papers  (2026-04-13T14:58:15Z)
• Information Hidden in Gradients of Regression with Target Noise [2.8911861322232686]
  We show that the gradients alone can reveal the Hessian.<n>We provide non-asymptotic operator-norm guarantees under sub-Gaussian inputs.
  arXiv  Detail & Related papers  (2026-01-26T14:50:16Z)
• MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models [86.07486858219137]
  Diffusion models excel at generating images conditioned on text prompts.<n>The resulting images often do not satisfy user-specific criteria measured by scalar rewards such as Aesthetic Scores.<n>Recently, inference-time alignment via noise optimization has emerged as an efficient alternative.<n>We show that this approach suffers from reward hacking, where the model produces images that score highly, yet deviate significantly from the original prompt.
  arXiv  Detail & Related papers  (2025-10-02T00:47:36Z)
• Treeffuser: Probabilistic Predictions via Conditional Diffusions with Gradient-Boosted Trees [39.9546129327526]
  Treeffuser is an easy-to-use method for probabilistic prediction on tabular data. Treeffuser learns well-calibrated predictive distributions and can handle a wide range of regression tasks. We demonstrate its versatility with an application to inventory allocation under uncertainty using sales data from Walmart.
  arXiv  Detail & Related papers  (2024-06-11T18:59:24Z)
• Rejection via Learning Density Ratios [50.91522897152437]
  Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions.<n>We propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance.<n>Our framework is tested empirically over clean and noisy datasets.
  arXiv  Detail & Related papers  (2024-05-29T01:32:17Z)
• Variational Deep Survival Machines: Survival Regression with Censored Outcomes [11.82370259688716]
  Survival regression aims to predict the time when an event of interest will take place, typically a death or a failure. We present a novel method to predict the survival time by better clustering the survival data and combine primitive distributions.
  arXiv  Detail & Related papers  (2024-04-24T02:16:00Z)
• Certifying Confidence via Randomized Smoothing [151.67113334248464]
  Randomized smoothing has been shown to provide good certified-robustness guarantees for high-dimensional classification problems. Most smoothing methods do not give us any information about the confidence with which the underlying classifier makes a prediction. We propose a method to generate certified radii for the prediction confidence of the smoothed classifier.
  arXiv  Detail & Related papers  (2020-09-17T04:37:26Z)
• Preventing Posterior Collapse with Levenshtein Variational Autoencoder [61.30283661804425]
  We propose to replace the evidence lower bound (ELBO) with a new objective which is simple to optimize and prevents posterior collapse. We show that Levenstein VAE produces more informative latent representations than alternative approaches to preventing posterior collapse.
  arXiv  Detail & Related papers  (2020-04-30T13:27:26Z)

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.