paper-with-me

Papers

OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning

2026-03-25 · Kaihang Pan, Qi Tian, Jianwei Zhang, Weijie Kong, Jiangfeng Xiong, Yanxin Long, Shixue Zhang, Haiyi Qiu, Tan Wang, Zheqi Lv, Yue Wu, Liefeng Bo, Siliang Tang, Zhao Zhong arxiv

While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, open-source alternatives significantly lag behind. Most academic models remain heavily fragmented, and the few existing efforts toward unified video generation still struggle to seamlessly integrate diverse tasks within a single framework. To bridge this gap, we propose OmniWeaving, an omni-level video generation model featuring powerful multimodal composition and reasoning-informed capabilities. By leveraging a massive-scale pretraining dataset that encompasses diverse compositional and reasoning-augmented scenarios, OmniWeaving learns to temporally bind interleaved text, multi-image, and video inputs while acting as an intelligent agent to infer complex user intentions for sophisticated video creation. Furthermore, we introduce IntelligentVBench, the first comprehensive benchmark designed to rigorously assess next-level intelligent unified video generation. Extensive experiments demonstrate that OmniWeaving achieves SoTA performance among open-source unified models. The codes and model have already been publicly available. Project Page: https://omniweaving.github.io.

📄 PDF Abstract BibTeX arXiv:2603.24458

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

2026-07-29 · Haodong Li, Tianfei Ren, Xiaoxiao Ma, Chunmei Qing 외 hf

Text-to-video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal evolution of a scene must be inferred implicitly from a highly compres…

Video Generation

UniVG: Towards UNIfied-modal Video Generation

2024-01-17 · Ludan Ruan, Lei Tian, Chuanwei Huang, Xu Zhang 외

Diffusion based video generation has received extensive attention and achieved considerable success within both the academic and industrial communities. However, current efforts are mainly concentrated on single-objectiv…

Video Generation

CineWeaver: Training-Free Reference-Controllable Multi-Shot Long Video Generation for Cinematic Storytelling

2026-07-29 · Yuyang Huang, Yabo Chen, Wenrui Dai, Ziyang Zheng 외 arxiv

Cinematic video generation is challenging for text-to-video diffusion models due to concurrent requirements on multi-shot generation, fine-grained controllability over characters and scenes, and long-form generation acro…

Video Generation

UniVideo: Unified Understanding, Generation, and Editing for Videos

2025-10-09 · Cong Wei, Quande Liu, Zixuan Ye, Qiulin Wang 외 arxiv

Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends un…

Video GenerationText GenerationStyle TransferImage Editing

FIFA: Unified Faithfulness Evaluation Framework for Text-to-Video and Video-to-Text Generation

2025-07-09 · Liqiang Jing, Viet Lai, Seunghyun Yoon, Trung Bui 외

Video Multimodal Large Language Models (VideoMLLMs) have achieved remarkable progress in both Video-to-Text and Text-to-Video tasks. However, they often suffer fro hallucinations, generating content that contradicts the …

DescriptiveText GenerationVideo Generation