ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)

miHoYo's research team describes Gamer, a vision-language-action framework submitted on November 13 and revised on November 18. The model builds on Qwen3-VL-8B to turn screen observations into keyboard and mouse actions for long-horizon game control without relying on internal game interfaces.
Tap to vote and see what everyone thinks.
Summary by ByteBrief