# PreCoG: Preview-Edit for Efficient Video Correction in Generation-Time

arXiv: https://arxiv.org/abs/2610.13174 · HTML: https://mlsanity.com/paper/2610.13174/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 23 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 19 of 19)

- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2302.04867/) (2023)
- [FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models](https://mlsanity.com/paper/2412.08629/) (2024)
- [T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation](https://mlsanity.com/paper/2407.14505/) (2024)
- [Helios: Real Real-Time Long Video Generation Model](https://mlsanity.com/paper/2603.04379/) (2026)
- [Boosting Diffusion Models with Moving Average Sampling in Frequency Domain](https://mlsanity.com/paper/2403.17870/) (2024)
- [Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search](https://mlsanity.com/paper/2501.19252/) (2025)
- [Video-T1: Test-Time Scaling for Video Generation](https://mlsanity.com/paper/2503.18942/) (2025)
- [VISTA: A Test-Time Self-Improving Video Generation Agent](https://mlsanity.com/paper/2510.15831/) (2025)
- [FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing](https://mlsanity.com/paper/2506.05046/) (2025)
- [GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration](https://mlsanity.com/paper/2412.04440/) (2024)
- [FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models](https://mlsanity.com/paper/2503.13684/) (2025)
- [Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement](https://mlsanity.com/paper/2411.15115/) (2024)
- [VQQA: An Agentic Approach for Video Evaluation and Quality Improvement](https://mlsanity.com/paper/2603.12310/) (2026)
- [We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback](https://mlsanity.com/paper/2504.17180/) (2025)
- [LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion](https://mlsanity.com/paper/2603.14526/) (2026)
- [Image Diffusion Preview with Consistency Solver](https://mlsanity.com/paper/2512.13592/) (2025)
- [CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusion](https://mlsanity.com/paper/2607.23159/) (2026)
- [FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing](https://mlsanity.com/paper/2604.22586/) (2026)

## Abstract (arXiv)

Iterative text-to-video generation relies on feedback to correct compositional and temporal failures. However, existing methods typically require another full generation run for each correction, repeating computation and potentially disrupting already correct content. We introduce PreCoG, an iterative framework for correcting semantic failures during video generation. PreQA diagnoses failures from low-cost previews and constructs corrective conditions, while PreEdit edits cached generation trajectories under these conditions, attenuating orthogonal changes to limit disruption of already correct content. PreCoG completes generation only for the selected candidate, reusing its cached trajectory to reduce redundant computation and help preserve semantic consistency between the preview and the final video. Experiments show that PreCoG achieves the highest VBench and T2V-CompBench scores and approaches VSR's leading VS2 score at 0.56× its inference time. It also outperforms GENMAC on all three quality and alignment metrics at 0.86× its inference time.