# Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search

arXiv: https://arxiv.org/abs/2501.19252 · HTML: https://mlsanity.com/paper/2501.19252/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 76 of its 111 references that are in the map.
- First posted on arXiv 31 Jan 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 76)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)

## Built on by (most cited first, 30 of 41)

- [RewardDance: Reward Scaling in Visual Generation](https://mlsanity.com/paper/2509.08826/) (2025)
- [Scaling Image and Video Generation via Test-Time Evolutionary Search](https://mlsanity.com/paper/2505.17618/) (2025)
- [TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation](https://mlsanity.com/paper/2507.18537/) (2025)
- [ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos](https://mlsanity.com/paper/2503.16400/) (2025)
- [RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling](https://mlsanity.com/paper/2510.20206/) (2025)
- [ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints](https://mlsanity.com/paper/2510.14847/) (2025)
- [MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation](https://mlsanity.com/paper/2511.22989/) (2025)
- [WorldPack: Dynamic Frame Compression for Long-context Video World Modeling](https://mlsanity.com/paper/2512.02473/) (2025)
- [From Scale to Speed: Adaptive Test-Time Scaling for Image Editing](https://mlsanity.com/paper/2603.00141/) (2026)
- [Adaptive Inference-Time Scaling via Cyclic Diffusion Search](https://mlsanity.com/paper/2505.14036/) (2025)
- [Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance](https://mlsanity.com/paper/2510.10402/) (2025)
- [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026)
- [Fast Monte Carlo Tree Diffusion: 100x Speedup via Parallel Sparse Planning](https://mlsanity.com/paper/2506.09498/) (2025)
- [AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path](https://mlsanity.com/paper/2512.11203/) (2025)
- [Stream-T1: Test-Time Scaling for Streaming Video Generation](https://mlsanity.com/paper/2605.04461/) (2026)
- [Inference-Time Scaling for Joint Audio-Video Generation](https://mlsanity.com/paper/2606.03183/) (2026)
- [Temporal Backtracking Search for Test-time Generative Video Reasoning](https://mlsanity.com/paper/2606.13861/) (2026)
- [GEOPHYS: The Geometry of Physical Plausibility](https://mlsanity.com/paper/2606.20707/) (2026)
- [Compositional Monte Carlo Tree Diffusion for Extendable Planning](https://mlsanity.com/paper/2510.21361/) (2025)
- [Gradient Preconditioning for Efficient and Reliable Reward-Guided Generation](https://mlsanity.com/paper/2602.08646/) (2026)
- [Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling](https://mlsanity.com/paper/2605.05922/) (2026)
- [Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation](https://mlsanity.com/paper/2607.14962/) (2026)
- [Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations](https://mlsanity.com/paper/2506.20294/) (2025)
- [Seeking Physics in Diffusion Noise](https://mlsanity.com/paper/2603.14294/) (2026)
- [Early Failure Detection and Intervention in Video Diffusion Models](https://mlsanity.com/paper/2603.14320/) (2026)
- [Tuning Real-World Image Restoration at Inference: A Test-Time Scaling Paradigm for Flow Matching Models](https://mlsanity.com/paper/2603.22027/) (2026)
- [StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement](https://mlsanity.com/paper/2606.00267/) (2026)
- [SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation](https://mlsanity.com/paper/2606.11969/) (2026)
- [History-Conditioned Joint-Prefix Alignment for Generative Recommendation](https://mlsanity.com/paper/2608.29179/) (2026)
- [Unified Control for Inference-Time Guidance of Denoising Diffusion Models](https://mlsanity.com/paper/2512.12339/) (2025)

## Abstract (arXiv)

The remarkable progress in text-to-video diffusion models enables the generation of photorealistic videos, although the content of these generated videos often includes unnatural movement or deformation, reverse playback, and motionless scenes. Recently, an alignment problem has attracted huge attention, where we steer the output of diffusion models based on some measure of the content's goodness. Because there is a large room for improvement of perceptual quality along the frame direction, we should address which metrics we should optimize and how we can optimize them in the video generation. 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 at inference time. We then point out that improving perceptual video quality with respect to alignment to prompts requires reward calibration by weighting existing metrics. This is because when humans or vision language models evaluate outputs, many previous metrics to quantify the naturalness of video do not always correlate with the evaluation. We demonstrate that our method improves the perceptual quality evaluated on the calibrated reward, VLMs, and human assessment, without model parameter update, and outputs the best generation compared to greedy search and best-of-N sampling under much more efficient computational cost. The experiments highlight that our method is beneficial to many capable generative models, and provide a practical guideline: we should prioritize the inference-time compute allocation into enabling the lookahead estimator and increasing the search budget, rather than expanding the denoising steps.