Xiangtai Li

5 papers ByteDance Inc.

• AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding
• Conditional Panoramic Image Generation via Masked Autoregressive Modeling
• MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
• UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions
• VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models