VIDiff is a unified foundation model that uses diffusion techniques to perform a broad range of video tasks, including both understanding tasks like language‑guided video object segmentation and generative tasks such as video editing and enhancement. Unlike prior methods that focus on short clips and require time‑consuming tuning, VIDiff can edit and translate videos within seconds based on user instructions and employs an iterative auto‑regressive approach to maintain consistency in long‑form videos. The authors demonstrate convincing generative results across diverse input videos and written instructions, supported by qualitative and quantitative evidence.
By Zhen Xing, Shuyuan Tu, Qi Dai, Zihao Zhang, Hui Zhang, Han Hu, Zuxuan Wu, Yu-Gang Jiang
Edit‑VAR is a training‑free, inversion‑free framework that uses a pretrained visual autoregressive video model for text‑guided video editing. It encodes the source video into multi‑scale discrete tokens and applies probability‑guided conditional token replacement, attention‑guided token‑wise and scale‑aware modulation, and scale‑decoupled generation to preserve source appearance while enabling precise edits. The method also includes residual‑guided token pruning to reduce inference cost, and experimental results show it outperforms existing training‑free video editing methods in fidelity, source preservation, temporal coherence, and efficiency.
By Chongbo Zhao, Jiangming Wang, Xilai Wang, Xinyu Wang, Jingyi Tang, Chunjie Hao, Pengjie Song, Yue Ma
Memory-V2V is a memory‑augmented video‑to‑video diffusion framework designed to improve cross‑turn consistency in multi‑turn video editing. It stores previous outputs in an external memory, retrieves relevant edits, and incorporates them via relevance‑aware tokenization and adaptive compression, allowing scalable conditioning without linear computational growth. Experiments on iterative video novel view synthesis and text‑guided long video editing show that Memory‑V2V enhances consistency while preserving visual quality and outperforming strong baselines with modest overhead.
By Dohun Lee, Chun-Hao Paul Huang, Xuelin Chen, Jong Chul Ye, Duygu Ceylan, Hyeonho Jeong
arXiv:2606. 11751v1 Announce Type: cross Abstract: Multi-turn image editing is essential for iterative design, yet current models often struggle with identity drift and error accumulation over successive steps.
By Hang Xu, Xiaoxiao Ma, Guohui Zhang, Yu Hu, Siming Fu, Jie Huang, Lin Song, Haoyang Huang, Nan Duan, Feng Zhao
arXiv:2607. 19895v1 Announce Type: cross Abstract: Text-guided video editing with diffusion models is impractically slow, hindered by costly multi-step sampling and inversion.
By Habin Lim, Gyeong-Moon Park
Recent diffusion editors perform diverse instruction-based edits while conditioning on the source image at every denoising step. Yet persistent source-image conditioning can limit how fully an edit is executed and how natural the result appears, especially when the target scene diverges substantially from the input.
Ring Forcing is an autoregressive video diffusion framework that enhances long‑term memory by enforcing retrieval from distant history through a ring‑structured training strategy. It introduces a compression and timestep composition method to extend effective historical span to minutes, and a sparse RoPE mechanism for scalable memory adaptation. Experiments show that Ring Forcing outperforms state‑of‑the‑art models in minutes‑long coherence and object permanence.
By Bowen Xue, Brandon Y. Feng, Chenguo Lin, Yuchen Lin, Yujia Zeng, Lvmin Zhang, Maneesh Agrawala, Honglei Yan, Panwang Pan
Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. However, existing methods are restricted to forward temporal generation, whereas practical video creation often requires flexible generation order, e.
Recent advances in diffusion models and Transformer architectures have led to significant progress in text-to-video generation. However, these models often suffer from semantic errors such as missing...
The paper introduces Relax Forcing, a training‑free memory mechanism for autoregressive video diffusion that structures temporal context into Sink, Tail, and History frames. By selecting History frames with a relaxation criterion, the method reduces error accumulation and attention overhead while preserving motion dynamics. Experiments on VBench‑Long demonstrate that this structured memory improves long‑video generation quality over existing baselines.
By Zengqun Zhao, Yanzuo Lu, Ziquan Liu, Jifei Song, Jiankang Deng, Ioannis Patras
arXiv:2608. 16513v1 Announce Type: cross Abstract: Recent advances in diffusion models and Transformer architectures have led to significant progress in text-to-video generation.
By Junhao Chen, Zheqi Lv, Keting Yin, Shengyu Zhang, Zhou Zhao, Feiyang Chen, Xinyu Duan, Baoxing Huai, Fei Wu
arXiv:2509.25998v4 Announce Type: replace
Abstract: In light of recent progress in video editing, deep learning models focusing on both spatial and temporal dependencies have emerged as the primary m...
By Abdelilah Aitrouga, Youssef Hmamouche, Amal El Fallah Seghrouchni