Papers

Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.

Filtered by domain: scene-text-recognitionClear

TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming

21 Aug 2026

E-commerce live streaming requires omni-modal understanding of noisy, temporally extended streams, where product facts are distributed across speech, video frames, product images, overlaid text, and user queries.

Automatic Speech Recognition Omni models Reinforcement Learning Scene Text Recognition

1000.3/h