TaoLiveAIGC/TBDub
Video-to-Video • Updated • 106 • 2
AI & ML interests
None defined yet.
Recent Activity
Papers
Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report
TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming
Organization Card
🍑 TaoLiveAIGC Team 
Taobao & Tmall Group
We are the TaoLiveAIGC Team at Taobao & Tmall, Alibaba Group, building next-generation digital humans for live commerce. Our work spans speech, LLMs, video generation, and multimodal intelligence, enabling natural and real-time interaction at scale.
- Github: https://github.com/TaoLiveAIGC
- Huggingface: https://huggingface.co/TaoLiveAIGC
💻 Research Projects
🎙️ TTS
- Qwen3-TTS-TBLive: Live-Streaming Domain-adaption Built on Qwen3-TTS-1.7B Base model
🧠 Large Language Model
🎥 Video Generation
TBDub: Production-Oriented Visual Dubbing
CoInteract: Spatially-Structured Co-Generation for Interactive Human-Object Video Synthesis
TaoMate: Anchor-Guided Memory Bridging Evolving and Reference States for Real-Time Audio-Video Digital Human Generation
TaoMate-H3: TaoMate training with MiniMax H3
AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars
🌐 Multimodal Large Language Model
- TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming
models 8
TaoLiveAIGC/TaoMate-H3
Text-to-Video • Updated • 175 • • 45
TaoLiveAIGC/TLive-Omni-9B
Text Generation • 10B • Updated • 1.33k • 15
TaoLiveAIGC/TLive-Omni-4B
Text Generation • 6B • Updated • 1.93k • 18
TaoLiveAIGC/TaoMate
Text-to-Video • Updated • 2.35k • 3
TaoLiveAIGC/Qwen3-TTS-TBLive-Base
Text-to-Speech • 2B • Updated • 37 • 1
TaoLiveAIGC/Qwen3-TTS-TBLive-CustomVoice
Text-to-Speech • 2B • Updated • 44 • 1
TaoLiveAIGC/AptAvatar
19B • Updated • 461 • 3
datasets 0
None public yet