Search AI News
Find articles across all categories and topics
2 results for "causal architecture"
StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars
arXiv:2512.22065v2 Announce Type: replace-cross Abstract: Real-time, streaming interactive avatars represent a critical yet challenging goal in digital human research. Although diffusion-based human avatar generation methods achieve remarkable success, their non-causal architecture and high computational costs make them unsuitable for streaming. Moreover, existing interactive approaches are typically restricted to the head-and-shoulder region, limiting their ability to produce gestures and body motions. To address these challenges, we propose a two-stage autoregressive adaptation and accelerat — Zhiyao Sun, Ziqiao Peng, Yifeng Ma, Yi Chen, Zhengguang Zhou, Zixiang Zhou, Guozhen Zhang, Youliang Zhang, Yuan Zhou, Qinglin Lu, Yong-Jin Liu
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
ShotStream enables real-time interactive multi-shot video generation through causal architecture design, dual-cache memory mechanisms, and two-stage distillation to maintain visual consistency and reduce latency. (45 upvotes on HuggingFace)