Firehose

29 OCT 2026 · Paper

Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities

This paper introduces Youtu-Parsing-Omni, a system that can parse documents, images, audio, and video into structured records, allowing agents to access and cite evidence across multiple modalities. Practitioners might care about this research because it provides a new approach to multimodal parsing that can improve the performance of agents in various applications.

multimodal parsing vision-language models continual learning agents benchmarks

Browse by tag

Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities