Skip to content
Live
Trending storyPast story

StreamDuo live commentary system released

1 reports1 outlets14 days agoUpdate

The story so far

AI overview

Hugging Face Daily Papers reports that the StreamDuo system pairs a trainable narrator with a frozen research agent, enhancing cross-game live commentary effectiveness by retrieving game wiki entries. The system was trained on Baldur's Gate 3 and tested in ten unseen new games, improving entity recall from 0.082 to 0.116 and reducing source game leakage from 9.9% to 1.0%, performing best in live models. StreamDuo's design aims to improve the quality of cross-game live commentary without the need for training specifically for the target game. This improvement is achieved by using a frozen research agent to retrieve game wiki entries, effectively reducing leakage rates and improving recall.

AI-written from the reports · Updated 13 days ago

Coverage timeline

Follow the coverage to see every side of the story.

5 Nov
  1. Hugging Face Daily Papers
    StreamDuo: A Live Commentator and a Research Agent for Unseen Games

    StreamDuo pairs a trainable commentator with a frozen research agent that searches for game wiki entries to improve cross-game live commentary without training specifically for the target game. StreamDuo was trained on Baldur's Gate 3 and tested on ten unseen new games, increasing entity recall from 0.082 to 0.116, reducing source game leakage from 9.9% to 1.0%, and achieving the best timing, highest evaluation vitality, and overall quality in the live model.