6 papers
PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialogue
Shibo Wang, Zicheng Zhang, Libo Wang +1
LLM-based full-duplex voice services allow users to speak while the assistant is responding. Because servers can generate output and advance dialogue state faster than clients can…
TaoMate: Anchor-Guided Memory Bridging Evolving and Reference States for Real-Time Audio-Video Digital Human Generation
Qijun Gan, Chenwei Zhang, Meiguang Jin +2
Real-time long-form digital-human generation relies on causal models to extend audio-visual content while preserving subject appearance and audio-video synchronization across succe…
AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars
Hengyuan Zhang, Jingna Sun, Meiguang Jin +1
Production-ready audio-driven avatar generation requires efficient inference without sacrificing fidelity or motion expressiveness. However, existing acceleration methods often com…
Attention Grounded Enhancement for Visual Document Retrieval
Wanqing Cui, Wei Huang, Yazhi Guo +4
Visual document retrieval requires understanding heterogeneous and multi-modal content to satisfy implicit information needs. Recent advances use screenshot-based document encoding…
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
Xiangyang Luo, Xiaozhe Xin, Tao Feng +3
Synthesizing human--object interaction (HOI) videos has broad practical value in e-commerce, digital advertising, and virtual marketing. However, current diffusion models, despite…
LiveThinking: Enabling Real-Time Efficient Reasoning for AI-Powered Livestreaming via Reinforcement Learning
Yuhan Sun, Zhiwei Huang, Wanqing Cui +4
In AI-powered e-commerce livestreaming, digital avatars require real-time responses to drive engagement, a task for which high-latency Large Reasoning Models (LRMs) are ill-suited.…