SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation
Yining Hong, Beide Liu, Maxine Wu, Yuanhao Zhai, Kai-Wei Chang, Linjie Li, Kevin Lin, Chung-Ching Lin, Jianfeng Wang, Zhengyuan Yang, Ying Nian Wu, Lijuan Wang
Abstract
Published as a conference paper at ICLR 2025 compared to 782, and maintaining consistency in longer videos, with an average of 0.37 scene cuts versus 0.89. The slow-fast learning loop algorithm significantly enhances performances on long-horizon planning tasks as well.
Ask Lune
Ask anything. The answer quotes the paper.
Lune reads all of it and the papers around it, then shows you the passages behind every answer.
Lune answers from
the full paper · 11 top-tier papers that cite it · related work
Free to start. No credit card required.
Cited by top-tier papers11
- WorldMem: Long-term Consistent World Simulation with MemoryZeqi Xiao, Yushi Lan, Yifan Zhou, Wenqi Ouyang et al.NeurIPS 2025 · 165 citations
- Video World Models with Long-term Spatial MemoryTong Wu, Shuai Yang, Ryan Po, Yinghao Xu et al.NeurIPS 2025 · 145 citations
- Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion ModelsLvmin Zhang, Shengqu Cai, Muyang Li, Gordon Wetzstein et al.NeurIPS 2025 · 132 citations
- Learning World Models for Interactive Video GenerationTaiye Chen, Xun Hu, Zihan Ding, Chi JinNeurIPS 2025 · 37 citations
- Learning 3D Persistent Embodied World ModelsSiyuan Zhou, Yilun Du, Yuncong Yang, Lei Han et al.NeurIPS 2025 · 34 citations
Builds on18
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Video Diffusion ModelsJonathan Ho, Tim Salimans, Alexey A. Gritsenko, William Chan et al.NeurIPS 2022 · 2,948 citations
- AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific TuningYuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang et al.ICLR 2024 · 1,493 citations
Related papers
- LoViC: Efficient Long Video Generation with Context CompressionJiaxiu Jiang, Wenbo Li, Jingjing Ren, Yuping Qiu, Renjing Pei, Fenglong Song, Yong Guo, Xiaogang Xu, Han Wu, Wangmeng ZuoCVPR Findings 2026
- Driving Into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous DrivingYuqi Wang, Jiawei He, Lue Fan, Hongxin Li et al.CVPR 2024
- Scene Consistency Representation Learning for Video Scene SegmentationHaoqian Wu, Keyu Chen, Yanan Luo, Ruizhi Qiao et al.CVPR 2022 · 19 citations
- StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene GenerationShangjin Zhai, Zhichao Ye, Jialin Liu, Weijian Xie et al.CVPR 2025
- FastFlow: Accelerating The Generative Flow Matching Models with Bandit InferenceDivya Jyoti Bajpai, Dhruv Bhardwaj, Soumya Roy, Tejas Duseja et al.ICLR 2026 · 3 citations
