Vidi Collection Vidi model collection for multimodal video understanding and creation • 2 items • Updated Jan 22 • 3
OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer Paper • 2601.14250 • Published Jan 20 • 47
What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study Paper • 2506.12537 • Published Jun 14, 2025 • 1
Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training Paper • 2502.04066 • Published Feb 6, 2025
TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities Paper • 2407.21693 • Published Jul 31, 2024
Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control Paper • 2601.03973 • Published Jan 7 • 2
The Role of Entropy in Visual Grounding: Analysis and Optimization Paper • 2512.06726 • Published Dec 7, 2025 • 1