Skip to content

PreviewDiff: Multimodal Critic-Guided Search over Diffusion Latents

Sep 2026 · arXiv.org · Vol abs/2609.36199 · 0 citations · 42 references
Computer Science

Abstract

Diffusion models can produce striking images and videos, but they still struggle with the compositional details that make a generation faithful to a prompt, such as object counts, attribute binding, spatial relations, and temporally grounded actions. A common way to improve prompt satisfaction is to spend more compute at test time through Best-of-N sampling, but final-sample selection is fixed. Best-of-N can only choose among completed outputs and cannot repair a promising trajectory before it fails. We introduce PreviewDiff, a training-free test-time search method that turns diffusion sampling from scalar search into a multimodal critic-guided search over intermediate latents. At selected denoising checkpoints, PreviewDiff decodes a partial preview, asks a multimodal judge to score and critique it, and uses the resulting natural-language feedback to branch over semantic prompt edits and locally re-noised latent continuations. These branches are then scored and selectively rolled forward, allowing verifier compute to guide generation while the sample is still editable. Across image and video generation benchmarks, PreviewDiff consistently improves over budget-matched Best-of-N selection and strong scalar-search baselines. Ablations show that earlier interventions and increased search width provide the largest gains, while deeper search and additional semantic variants offer complementary improvements. PreviewDiff demonstrates that multimodal feedback is most useful not only as a final verifier, but as an active controller inside the denoising process.

View source

Similar papers

Preprint Aug 2026

NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation

NoisEasier serves as both a flexible alternative and a complementary enhancement to reward-based fine-tuning, establishing test-time scaling as an effective paradigm for controllable text-to-video generation.

Yu-Jiang Pu, Yu Kong · 1 citation
#computer vision Preprint Aug 2026

Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning

Latent-OPD is proposed, which augments OPD with trajectory-level latent distillation and introduces a progressive teacher-lookahead strategy, which aligns middle-to-late student layers with increasingly deeper teacher layers, establishing Latent-OPD as a highly effective approach to frame-efficient video reasoning.

Aoni Shen, Yongheng Zhang, Ying-Hui Li et al. · 2 citations
Preprint Aug 2026

VISTA: Test-Time Compositional Alignment for Visual Autoregressive Generation

VISTA is the first gradient-based test-time alignment framework for next-scale autoregressive image generation, and introduces the mechanisms needed to make such optimization stable across scales, together with an extensible objective space that any differentiable constraint on cross-attention can plug into.

Hossein Shahabadi, Niki Sepasian, Mahdieh Soleymani Baghshah · 0 citations

CAST: Causal Advantage-Structured Training with Spatially Grounded Compositional Rewards for Diffusion Models

CAST (Causal Advantage-Structured Training), an RL fine-tuning method for pretrained DMs, which identifies the denoising step at which each model fixes the objects and their spatial arrangement in the image and uses that timing to set the SDE window and uses them to spatially weight the SDE policy objective.

Shu Yu, Chao-Chao Lu · 0 citations
Sep 2026

ExploreNet: Learning Where to Explore in Diffusion GRPO

Across group-relative diffusion RL experiments, it is found that exploration is learnable, the shape of the exploration distribution outweighs its magnitude, and rollout quality is more effective than rollout quantity.

S. Li, Xiao-Chuang Han, Y. Tsvetkov et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Oct 28, 2026

Making machines that can listen

Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.