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.· 0 citations
Audio-driven streaming avatar generation requires real-time synthesis of speech-synchronized videos with dynamic and diverse motion. Self Forcing uses Distribution Matching Distillation (DMD) to distill bidirectional video diffusion models into causal, few-step generators for real-time streaming. However, DMD minimizes...
Zi-Han Su, Si-Wen Lu, Junhao Zhuang et al.· 1 citation
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.
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
Self Gradient Forcing (SGF), a two-pass training strategy that restores this missing memory-writing supervision within the native autoregressive training objective, using losses on future video latents to train the model to encode context into more effective causal memory.
Results indicate that memory, geometric control, and rollout-aware training provide a practical foundation for generating coherent stories and continuously evolving interactive worlds.
Nan Duan, Hao-Yang Huang, Wei-Yang Jin et al.· 4 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
