11 papers
SCIC: Scope- and Codebook-Aware Instruction Conditioning for Speaker-Adapted Expressive TTS
Longyu Lu, Zongwei Du, Mengtao Xing +4
Long-form live-streaming TTS requires context-dependent prosody and paragraph-level coherence. However, many existing instruction-based TTS systems use global or uniform conditions…
StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning
Naen Xu, Wanqing Cui, Yibo Hu +5
Large language models deployed as personalized assistants must reason over long, evolving interaction histories. However, in long-term dialogue reasoning, relevant evidence is scat…
Multi-Dimensional Prosody Judgment For Live Streaming Speech Synthesis
Zifan Guan, Longyu Lu, Junan Zhang +3
Evaluating live streaming speech synthesis (TTS) requires assessing fine-grained, highly expressive prosody such as emotion, intonation, and energy which traditional MOS predictors…
Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report
TaoLive AIGC LLM Team, Yuhan Sun, Wenhao Lin +7
AI-powered digital avatar streamers must answer product questions, engage viewers, and execute marketing strategies in real time, demanding low latency, frequent strategy updates,…
TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming
Yibo Hu, Yu Qian, Mao Gu +6
E-commerce live streaming requires omni-modal understanding of noisy, temporally extended streams, where product facts are distributed across speech, video frames, product images,…
OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models
Jinsen Su, Yongdong Luo, Yuexiao Ma +3
Existing token compression methods for omnimodal large language models typically rely on one modality to determine what to retain in the other. We show that this assumption often b…
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…
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…
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…
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…
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.…