Interactive video world models predict how an environment evolves under user actions, but most existing systems assume one controlled agent and one task-specific action interface. We study multi-agent video world modeling, where one model generates a joint visual future for multiple controlled agents while interpreting...
Xinyu Wang, Hua-Feng Shi, Yue Ma et al.· 0 citations
SonicWeave is proposed, a flow-matching model for unified audio scene generation that supports speech, music, sound effects, singing, and their fine-grained mixtures with a single set of weights and suggests that temporally coherent, prior-evidence routing is an effective conditional-computation strategy for unified au...
Yun-Rui Cai, Xu Li, Yucheng Zhou et al.· 0 citations
Music videos are an important form of audiovisual expression in contemporary culture. They translate and extend the expressive content of songs through deliberate visual design. Existing automatic music video (MV) generation systems can generate visually plausible shots, yet often struggle with long-form coherence and...
This work introduces SPACE (Subject-centric Poses, Appearance, and Characteristics Evaluation), a benchmark designed to evaluate subject-centered spatial understanding, and designs a rubric-based reward for Group Relative Policy Optimization that explicitly penalizes structurally critical spatial errors during alignmen...
Bozhou Li, Jia-Hang Zhang, Yue Ding et al.· 0 citations
EmotionDialogCN is introduced, a large-scale audiovisual-emotional dataset designed to capture authentic face-to-face communication and achieves an emotion distribution deviation from real human emotion statistics and consistent subject framing, translating into stable unimodal and multimodal performance across acousti...
This work proposes Vid-PRE (Video Prompt Reasoner and Enhancer), a model-agnostic prompt rewriter that offloads the cognitive burden of reasoning to a dedicated VLM, and introduces VWG-Bench, a comprehensive benchmark spanning 9 reasoning dimensions and 38 fine-grained tasks.
Meng Luo, Yi-Chen Liu, Jia-Hao Wang et al.· 1 citation
StreamHOI, a low-latency streaming framework for long-duration HOI video generation, finds that the standard sink-local memory design faces a trade-off in streaming HOI generation, and different transformer blocks show different historical-memory preferences for HOI regions and surrounding regions.
Ze-Jing Rao, Haoxian Zhang, Xiao-Qiang Liu et al.· arXiv.org· 2 citations
Video motion transfer aims to animate a target object using dynamics from a reference video. Existing formulations largely rely on fixed structural correspondence, which becomes ill-defined when reference and target objects differ substantially in morphology, articulation, or deformation mechanisms. We introduce Motion...
Zhixue Fang, Zhimin Zhang, Bi'an Du et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
