LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion

• URL: http://arxiv.org/abs/2603.14526v1
• Date: Sun, 15 Mar 2026 18:07:29 GMT
• Title: LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
• Abstract summary: We introduce a novel inference-time search mechanism that performs Reward-Guided Resampling and Pruning.<n>LatSearch consistently improves video generation across multiple evaluation dimensions compared to the baseline Wan2.1 model.
• Score: 87.42285185305813
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The recent success of inference-time scaling in large language models has inspired similar explorations in video diffusion. In particular, motivated by the existence of "golden noise" that enhances video quality, prior work has attempted to improve inference by optimising or searching for better initial noise. However, these approaches have notable limitations: they either rely on priors imposed at the beginning of noise sampling or on rewards evaluated only on the denoised and decoded videos. This leads to error accumulation, delayed and sparse reward signals, and prohibitive computational cost, which prevents the use of stronger search algorithms. Crucially, stronger search algorithms are precisely what could unlock substantial gains in controllability, sample efficiency and generation quality for video diffusion, provided their computational cost can be reduced. To fill in this gap, we enable efficient inference-time scaling for video diffusion through latent reward guidance, which provides intermediate, informative and efficient feedback along the denoising trajectory. We introduce a latent reward model that scores partially denoised latents at arbitrary timesteps with respect to visual quality, motion quality, and text alignment. Building on this model, we propose LatSearch, a novel inference-time search mechanism that performs Reward-Guided Resampling and Pruning (RGRP). In the resampling stage, candidates are sampled according to reward-normalised probabilities to reduce over-reliance on the reward model. In the pruning stage, applied at the final scheduled step, only the candidate with the highest cumulative reward is retained, improving both quality and efficiency. We evaluate LatSearch on the VBench-2.0 benchmark and demonstrate that it consistently improves video generation across multiple evaluation dimensions compared to the baseline Wan2.1 model.

Related papers

• Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models [91.19049123903137]
  Inference-time scaling for text-to-image generation has progressed from simple Best-of-$N$ sampling to guided search methods.<n>These approaches focus on when and how often to verify during denoising but largely treat the cost of generation itself as fixed.<n>We show that under wall-clock evaluation, simple BoN already matches or outperforms several guided search techniques.
  arXiv  Detail & Related papers  (2026-07-05T19:02:32Z)
• Temporal Backtracking Search for Test-time Generative Video Reasoning [51.4821857044108]
  generative video reasoning remains bottlenecked by a single-shot paradigm.<n>We introduce Temporal Backtracking Search (TBS), which shifts the search space to the temporal axis.<n>In a strict out-of-distribution setting, TBS achieves 22.7%, with every solved episode stemming from a restarted branch.
  arXiv  Detail & Related papers  (2026-06-11T19:41:18Z)
• TTSnap: Test-Time Scaling of Diffusion Models via Noise-Aware Pruning [53.52543819839442]
  A prominent approach to test-time scaling for text-to-image diffusion models formulates the problem as a search over multiple noise seeds.<n>We propose test-time scaling with noise-aware pruning (TTSnap), a framework that prunes low-quality candidates without fully denoising them.
  arXiv  Detail & Related papers  (2025-11-27T09:14:26Z)
• 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)
• Test-Time Scaling of Diffusion Models via Noise Trajectory Search [10.8507840358202]
  We introduce an $epsilon$-greedy search algorithm that globally explores at extreme timesteps and locally exploits during the intermediate steps where de-mixing occurs.<n>Experiments on EDM and Stable Diffusion reveal state-of-the-art scores for class-conditioned/text-to-image generation.
  arXiv  Detail & Related papers  (2025-05-24T19:13:29Z)
• Training-free Diffusion Acceleration with Bottleneck Sampling [37.9135035506567]
  Bottleneck Sampling is a training-free framework that leverages low-resolution priors to reduce computational overhead while preserving output fidelity.<n>It accelerates inference by up to 3$times$ for image generation and 2.5$times$ for video generation, all while maintaining output quality comparable to the standard full-resolution sampling process.
  arXiv  Detail & Related papers  (2025-03-24T17:59:02Z)
• ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos [41.45750971432533]
  Video diffusion models (VDMs) facilitate the generation of high-quality videos.<n>Recent studies have uncovered the existence of "golden noises" that can enhance video quality during generation.<n>We propose ScalingNoise, a plug-and-play inference-time search strategy that identifies golden initial noises for the diffusion sampling process.
  arXiv  Detail & Related papers  (2025-03-20T17:54:37Z)
• Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search [31.15452785332597]
  An alignment problem has attracted huge attention, where we steer the output of diffusion models based on some measure of the content's goodness.<n>In this paper, we propose diffusion latent beam search with lookahead estimator, which can select a better diffusion latent to maximize a given alignment reward.<n>We demonstrate that our method improves the perceptual quality evaluated on the calibrated reward, VLMs, and human assessment, without model parameter update.
  arXiv  Detail & Related papers  (2025-01-31T16:09:30Z)
• Enhancing Long Video Generation Consistency without Tuning [92.1714656167712]
  We address issues to enhance the consistency and coherence of videos generated with either single or multiple prompts.<n>We propose the Time-frequency based temporal Attention Reweighting Algorithm (TiARA), which judiciously edits the attention score matrix.<n>For videos generated by multiple prompts, we further uncover key factors such as the alignment of the prompts affecting prompt quality.<n>Inspired by our analyses, we propose PromptBlend, an advanced prompt pipeline that systematically aligns the prompts.
  arXiv  Detail & Related papers  (2024-12-23T03:56:27Z)

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.