acceptodds
Desk rejected at ICLR 2027

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

Desk rejected at ICLR 2027, so left out of the paper lists and the map.

Abstract

While proprietary systems such as Seedance have achieved remarkable success in omni-capable video generation, the academic research community lags far behind: most of its models remain heavily fragmented, and the few 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 academic unified models. Project page: https://anonymous.4open.science/r/omniweaving-24E4

Primary area:
generative models
Keywords:
Unified Video Generation

Related papers

Discussion (0)

Sign in to comment.