Egocentric action transfer aims to decouple the semantic action from egocentric observations and reproduce them in new visual contexts, enabling scalable world simulation, embodied policy learning, and robotic data generation. Existing approaches to transferring actions rely on condition-guided video generation, which...
Yue Ma, Peng-Jie Song, Xinyu Wang et al.· 0 citations
Video reward optimization can increase proxy rewards while reducing video dynamics, a mismatch we identify as \emph{motion collapse}, including under a video-level motion-quality reward. We propose \textbf{GraftOOD}, which replaces part of the online rollouts in selected prompt groups with out-of-distribution video exe...
Zhe-Ming Fu, R.-Z. He, Wen-Bin Ning et al.· 1 citation
This work proposes Representation Forcing, which learns few-step causal initialization through representation-space supervision rather than intermediate-teacher trajectory regression, and shows that, at four sampling steps, RepForcing better preserves generation quality than intermediate-teacher-based initialization be...
Si-Ming Fu, Zhe-Ming Fu, Lian-Rui Mu et al.· 0 citations
Few-step autoregressive video generation enables low-latency streaming, yet prevailing training pipelines separate causal adaptation from distribution matching. Recent representation-based text-to-video methods retain this separation by starting with an ODE initialization stage, even when the target distribution is def...
Hao-Jun Xu, Jie Huang, Chu-Yang Zhao et al.· 0 citations
Memory-based long-video generation aims to combine user control with long-range visual consistency. We organize this process into three functional components: a planner, an adapter, and a generator. Representative multi-shot systems couple memory to generator-specific interfaces or use predefined agent workflows, rathe...
Hang Xu, Guo-Hui Zhang, Xiao-Xiao Ma et al.· 0 citations
Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions. However, these two roles typically share parameters, and we find that their gradients exhibit distinct patterns and systematic negative alignment, hindering the joint op...
Zi-Han Su, Junhao Zhuang, Yao-Wei Li et al.· 4 citations· ⚡1
Routed Forcing is proposed, which routes the distillation objective by semantic region and noise stage to improve dynamics and diversity while preserving visual quality and lip synchronization in audio-driven streaming avatar generation.
Zi-Han Su, Si-Wen Lu, Junhao Zhuang et al.· arXiv.org· 1 citation
Improving robot policies on new tasks without collecting additional expert demonstrations remains a central challenge in robot learning. World action models (WAMs) use broad video priors to jointly predict future videos and actions, offering a potential source of supervision for adapting to new tasks. However, generate...
Shi-Long Zhou, Xiong-Hao Wu, Wen-Bo Li et al.· arXiv.org· 1 citation
WorldLine is introduced, an action-driven visual simulator that decouples transferable dynamics learning from heterogeneous action grounding and makes WorldLine a scalable and efficient visual simulator for policy evaluation and embodied planning.
EchoWM is an omnimodal world model for enterable generative media that responds to continuous navigation while jointly generating 720p video, environmental sound, music and speech, and maintains synchronized environmental sound and speech over long-horizon generation.
Across six real-world scenarios, human raters prefer JoyAI-VL-Interaction over the in-app video-call assistants of Doubao and Gemini by a wide margin, and the first open, vision-driven interaction model released together with its training recipe, data, and complete deployable system.
Ding-Yu Yao, Jun Zhou, Chenxu Yang et al.· arXiv.org· 10 citations
A large-scale synthetic data production pipeline built on Unreal Engine for generating action-conditioned, multi-view video, and describes the system architecture, the implementation decisions that emerged from production failures, and the limitations of using perceptual quality proxies for world-model data curation.
Hao-Yu Wang, Song-Chun Zhang, Hao-Ran Li 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.