We introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams, obtained by fine-tuning a pretrained V2V diffusion transformer on event-conditioned data built primarily from Ego4D. Given a monocular video and an event-triggered prompt of the form "when X happens, do Y," EgoPlay infers whether and when event X occurs, preserves pre-event frames, and applies edit Y only to the post-event continuation.
arXiv:2606. 02120v1 Announce Type: cross Abstract: In this report, we address the problem of determining whether a user performs an action incorrectly from egocentric video data.
By Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Ruochen Cui, Qingming Huang
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
Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term temporal consistency. We present JoyAI-Video-Edit, a 16B-parameter autoregressive diffusion framework for real-time, open-ended video editing without access to future frames or a predefined video duration.
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.
The quality and diversity of instruction-based video editing datasets are steadily improving, yet existing datasets mainly focus on single editing operations and fall short in supporting compositional instruction-guided video editing. In particular, multiple editing intents must be jointly understood and faithfully executed within the same video.
arXiv:2603. 13402v3 Announce Type: replace-cross Abstract: Current text-to-video models can make individual frames look convincing while still getting simple interactions wrong: objects move before contact, an intended action is skipped, a placed object keeps drifting, or a support relation breaks.
By Chika Maduabuchi, Jindong Wang
arXiv:2606. 19676v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image and video generation and editing.
By Haengbok Chung
arXiv:2607. 11523v1 Announce Type: cross Abstract: When should an intelligent assistant speak up without being asked?
By Gong Sitong, Tianyu Yan, Caixin Kang, Bo Zheng, Xiang Ruan, Huchuan Lu, Kaipeng Zhang, Yoichi Sato, Yifei Huang
arXiv:2605. 21917v2 Announce Type: replace-cross Abstract: Training Vision Language Models (VLMs) for video event reasoning requires high-quality structured annotations capturing not only what happened, but when, where, why, and with what consequence, at a scale manual labelling cannot support.
By Han Zhang, Wanting Jiang, Tomasz Kornuta, Tian Zheng, Vidya Murali
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
arXiv:2606. 13768v1 Announce Type: cross Abstract: Cinematic video depicts multiple subjects acting or interacting at specific moments, captured with deliberate camera movement, and stitched together by shot transitions.
By Sharath Girish, Tsai-Shien Chen, Zhikang Dong, Mukesh Singhal, Hao Chen, Sergey Tulyakov, Aliaksandr Siarohin