AI 学会了电竞导播：自己切镜头，自己解说
电竞直播里，导播和解说通常是两个人：一个决定切哪个选手的镜头，一个对着画面解说，而且谁都不知道下一秒会发生什么。现在有个叫 DirCast 的模型，把这两件事一个人全干了——它每秒扫一遍所有选手的摄像头(低分辨率)，决定切不切、切到谁，再只看被选中的那个画面(高分辨率)开口解说。它只靠过去的信息做判断，不偷看未来。在 27 场职业 Dota 2 比赛上，它切镜头的水平超过了规则算法和包括 GPT-5 在内的零样本模型，解说质量在对比评测里也赢了 GPT-4o。这不是你明天能用的东西，但它把「直播导演」这个需要临场判断、多路信息取舍的活，第一次交给了单个模型——意味着未来 AI 不仅能看懂比赛，还能决定观众看什么。
📄 原文摘要(英文)
A live esports broadcast needs a director who chooses which camera goes on air and a caster who talks over that choice, every second and without knowing what comes next. Streaming video language models have learned to commentate, but only over a broadcast that a human director has already produced. We study live broadcast production, in which a model receives the raw camera of every player and must both direct and commentate from the past alone. We present DirCast, a single streaming video language model that does both. Every second it scans all cameras at low resolution, decides with a hold-or-switch director whether and where to cut, and reads the chosen camera at high resolution before it speaks. Its context keeps what went on air and what was said and lets the other views expire, which bounds the cost of a stream of any length. We build a dataset of 27 professional Dota 2 matches with a camera for every hero, the human director's choices and the casters' commentary. DirCast directs better than rule-based and zero-shot directors including GPT-5, and its commentary wins 29.2 percent of comparisons against GPT-4o under the Proact-VL protocol, against 19.4 percent for the strongest of eleven streaming commentators that watch the human broadcast.